online transportation mode recognition and an application to...
Post on 21-Sep-2020
3 Views
Preview:
TRANSCRIPT
Online Transportation Mode Recognition
and an Application to Promote Greener
Transportation
Emil Hedemalm
Computer Science and Engineering, master's level (120 credits)
2017
Luleå University of Technology
Department of Computer Science, Electrical and Space Engineering
Luleå University of Technology
Department of Computer Science, Electrical and Space Engineering
Erasmus Mundus Master’s Programme in Pervasive Computing & Communications
for sustainable Development PERCCOM
Emil Hedemalm
Online Transportation Mode Recognition and an Application to Promote
Greener Transportation
2017
Supervisor(s) : Assoc. Prof. Josef Hallberg (Luleå University of Technology)
Dr. Ah-Lian Kor (Leeds Beckett University)
Professor Colin Pattinson (Leeds Beckett University)
Examiners: Prof. Eric Rondeau (University of Lorraine)
Prof. Jari Porras (Lappeenranta University of Technology)
Assoc. Prof. Karl Andersson (Luleå University of Technology)
ii
This thesis is prepared as part of an European Erasmus Mundus programme PERCCOM -
Pervasive Computing & COMmunications for sustainable development.
This thesis has been accepted by partner institutions of the consortium (cf. UDL-DAJ, n°1524, 2012
PERCCOM agreement).
Successful defence of this thesis is obligatory for graduation with the following national diplomas:
• Master in Complex Systems Engineering (University of Lorraine)
• Master of Science in Technology (Lappeenranta University of Technology
• Master of Science (120 credits) - Major; Computer Science and Engineering, Specialisation;
Pervasive Computing and Communications for Sustainable Development (Luleå University of
Technology)
iii
ABSTRACT
Luleå University of Technology
Department of Computer Science, Electrical and Space Engineering
Erasmus Mundus PERCCOM Master Program
Emil Hedemalm
Online Transportation Mode Recognition and an Application to Promote Greener
Transportation
Master’s Thesis
52 pages, 18 figures, 12 tables, 3 formulae, 12 appendixes
Examiners: Professor Eric Rondeau (Université de Lorraine)
Professor Jari Porras (Lappeenranta University of Technology)
Associate Professor Karl Andersson (Luleå University of Technology)
Keywords: Persuasive Design, Transportation Mode Detection, Serious Games, Sustainable
Behaviour
It is now widely accepted that human behaviour accounts for a large portion of total global
emissions, and thus influences climate change to a large extent [1]. Changing human behaviour
when it comes to mode of transportation is one component which could make a difference in
the long term. In order to achieve behavioural change, we investigate the use of a persuasive
multiplayer game. Transportation mode recognition is used within the game to provide bonuses
and penalties to users based on their daily choices regarding transportation. To easily identify
modes of transportation, an approach to transport recognition based on accelerometer and
gyroscope data is analysed and extended. Preliminary results from the machine learning tests
show that the classification true-positive rate for recognizing 10 different classes can reach up
to 95% when using a history set (66% without). Preliminary results from testers of the game
indicate that using games may be successful in causing positive change in user behaviour.
iv
ACKNOWLEDGEMENTS
This work is part of the Erasmus Mundus Master programme in Pervasive Computing and
Communication for Sustainable Development (PERCCOM) of the European Union [2] [3].
I would like to thank Andreas Söderberg for assisting with the graphical design of the game,
and Iris Panorel for helping with iterated tests while the game was being developed.
A big thanks to my supervisors, especially Josef Hallberg and Ah-Lian Kor, for their support
and feedback along the way.
As this thesis also marks the end of my time in the PERCCOM program, I also like to thank all
staff for their support and patience, especially Eric Rondeau. Also thanks to Jari for giving me
the great idea of conducting my thesis in Leeds, which I think was a good decision in retrospect.
1
TABLE OF CONTENTS
1 INTRODUCTION .............................................................................................. 4
1.1 GOALS AND DELIMITATIONS .................................................................................... 6
1.2 RESEARCH QUESTIONS ............................................................................................ 7
1.3 CONDUCT OF THE EXPERIMENT ............................................................................... 8
1.4 STRUCTURE OF THE THESIS ...................................................................................... 8
2 RELATED WORK .......................................................................................... 10
2.1 PERSUASIVE GAMES .............................................................................................. 10
2.2 TRANSPORTATION MODE RECOGNITION ............................................................... 11
3 UNDERLYING THEORIES ............................................................................ 13
3.1 MACHINE LEARNING ............................................................................................. 13
3.1.1 Machine Learning Definitions ....................................................................... 14 3.1.2 Random Forest ............................................................................................... 15 3.1.3 Random Tree .................................................................................................. 16
3.1.4 Bayesian Network ........................................................................................... 16 3.1.5 Naive Bayes .................................................................................................... 16
3.2 GAME DESIGN ....................................................................................................... 16
3.2.1 Challenge ....................................................................................................... 18
3.2.2 Uncertainty ..................................................................................................... 19 3.2.3 Fantasy ........................................................................................................... 19
3.2.4 Curiosity ......................................................................................................... 20
4 METHODOLOGY ........................................................................................... 22
4.1 PERSUASIVE GAME DEVELOPMENT ....................................................................... 22
4.1.1 System Architecture ........................................................................................ 22 4.1.2 Persuasive Game Requirements ..................................................................... 23 4.1.3 Applications developed .................................................................................. 24 4.1.4 Game Genre ................................................................................................... 25
4.1.5 Game Goals .................................................................................................... 25 4.1.6 Game Fantasy ................................................................................................ 26 4.1.7 Game Curiosity .............................................................................................. 26
4.1.8 Game Design details ...................................................................................... 27 4.2 EVALUATING BEHAVIOUR CHANGE ...................................................................... 28
4.3 GATHERING SENSOR SAMPLES ............................................................................... 29
4.4 TRANSPORTATION MODE DETECTION ................................................................... 30
4.4.1 Noise reduction by using a History set ........................................................... 31 4.4.2 Sleep sessions ................................................................................................. 32
2
4.4.3 Gravity measurement miscalibration ............................................................. 33
5 RESULTS ....................................................................................................... 35
5.1 GAME DESIGN ........................................................................................................ 35
5.2 GAME EVALUATION AND PERSUASIVE EFFECTS..................................................... 37
5.3 TRANSPORTATION MODE DATA SAMPLING ........................................................... 39
5.4 OFFLINE TRANSPORTATION MODE DETECTION ..................................................... 40
5.5 ONLINE TRANSPORTATION MODE DETECTION ...................................................... 44
6 DISCUSSION ................................................................................................. 46
7 CONCLUSIONS AND FUTURE WORK ........................................................ 49
REFERENCES ...................................................................................................... 50
APPENDIX
3
LIST OF SYMBOLS AND ABBREVIATIONS
BN Bayesian Network
CO2e Carbon dioxide equivalents
Evergreen Assaults of the Evergreen (the developed game)
HSS History set size
NB Naïve Bayesian
RF Random Forest
RT Random Tree
TP True-Positive
Weka The Weka 3 toolkit for Machine Learning and Data mining in Java [4] [5]
4
1 INTRODUCTION
This work presents an approach to change human behaviour by using persuasive serious games,
where the intention is to evaluate if and how we can decrease our overall carbon footprint. More
specifically, the work looks at changing behaviour when it comes to selecting modes of
transportation. According to Bin and Dowlatabadi [6], 22% of total emissions stem from
‘personal travel’, of which 68% comes from direct usage and 32% from indirect influences.
Therefore, transportation accounts for a large portion of our total emissions. If we could
influence our daily choices of transport it could therefore have a significant impact on the total
emissions.
As an example in Sweden, the overall emissions within the country has decreased over time
[7], making it seem like a good role model for change. Nevertheless, when studying the
emissions generated by Swedes outside of Sweden, the total emissions have increased as shown
in Figure 1. The data presented there, however, is mostly calculated on consumption and
investments of households, government and companies, and is not directly related to traffic-
related emissions.
If looking at emissions from transports within the same country (Sweden, see Figure 2), we can
see that it has slowly increased over time [8]. The major difference is that more emissions have
been generated outside of the country than inside it. This is likely attributed to increased
international travel. Of the total emissions generated by households, the Swedish authorities
Figure 2, Emissions from transports by Swedes within and outside of Sweden, as well as the total emissions from both [8].
Figure 1, Emissions emitted by Swedes within and outside of Sweden in million tons of carbon-dioxide equivalents [7]. The emissions have decreased within Sweden by 30%, but increased by 50% outside of the country million.
5
stated that 30% of them were emitted by transports. Another conclusion of the statistics from
Sweden is that transportation has come to take a bigger role in the emissions generated,
increasing from around 17% in 1990 to nearly 20% in 2014 (since the total emissions have
remained rather consistent at around 100 million tons of carbon-dioxide equivalents).
One might also want to have a look at the statistics of flight journeys per inhabitant and year
(see Figure 3) [9]. During the past 30-40 years travel by flight has been popularized and
increased drastically. Assuming the trend continues, flight journeys may have an increasing
effect on total carbon emissions.
When analysing everything in the larger context, then population growth emerges as one of the
biggest – if not the biggest – environmental issue of our time [10]. This includes reproductive
rights and is surrounded by numerous ethical concerns. Although it is arguably one of the most
important factors contributing to the detriment of environmental sustainability, it is not a topic
that will be covered further in this work.
The world population is projected to reach 9.7 billion by 2050 [11], exceeding 8.5 billion by
2030. Having these numbers in mind, there are primarily two options left to secure
environmental sustainability: one is via technical solutions and new inventions, the other via
other behavioural changes. Seeing as technical solutions only can help us insofar as we learn
and adapt to use them, one could argue that behaviour change may be the most crucial point to
achieving environmental sustainability in the future [12].
One issue with technology-driven gains is that they may be undermined by lifestyle changes
such as increased consumption – also known as the ‘rebound effect’ or Jevons paradox. One
Figure 3, Number of flights per inhabitant and year, as reported by the Swedish Environmental Protection Agency [9].
6
example mentioned by the European Environment Agency concerns the car transport sector,
where they state,
“Efficiency improvements are often insufficient to guarantee a decline in environmental
pressure. … This trend is apparent in the transport sector. Although fuel efficiency and emission
characteristics of cars improved …, rapid growth in car ownership and in kilometres driven
offset the potential improvements.” (page 102, State and Outlook 2015, Synthesis report [13])
Taking the aforementioned statement into consideration, this thesis focuses primarily on a way
to change behaviour using technology rather than a direct technical solution.
In order to achieve behavioural change, we have to consider all stages of change. Information
is a key element to begin to contemplate change, and strong motivators are key elements for
maintaining change. These elements are all prominent in games, making them a viable medium
to persuade users for behaviour change.
In this work, a prototype persuasive game is built. Using techniques from augmented reality
and transport detection via machine learning algorithms, it strives to give a personal feedback
loop to users. Daily actions will give repercussions within the game world, stimulating
behaviour change. The prototype game also has embedded multiplayer interactions, as this is
often lacking in contemporary serious games.
1.1 Goals and delimitations
As described in the previous section, the issue of global climate change is not improving, and
reductions to emissions need to be addressed.
This thesis aims to both study behaviours when it comes to mode of transportation, and try to
influence or alter them. Assuming this is successful, it could be one of many steps to try and
decrease our total carbon emissions and sustain the planet. If the gamification and persuasive
game techniques are effective, they could also possibly be applied in other fields to decrease
emissions as well.
In this thesis, a prototype persuasive game is developed and tested in order to influence or alter
behavioural patterns. A feedback system is included in the prototype in order to create a bond
between real-life actions and consequences within the game. The game is designed and
7
developed with common and popular features from the competitive game-market in order to
create a persuasive game and to persuade users to change their behaviour. This includes
multiplayer interactions and hints of augmented reality (via the feedback-loop). The game is
tested and evaluated to see how well behavioural change could be achieved by users playing
the game.
This thesis also aims to increase awareness of the environmental footprint of us all, since
behaviour change on any scale may be difficult to accomplish. If information really is a key to
change - and it is - then any enthusiasm into the game could potentially result in changes on the
long-term that will not be visible in the results presented at the end of this thesis.
As this thesis also is technical, it studies the entire progress of developing the serious game, as
well as how to efficiently use machine learning algorithms in modern smart-phone games
without impacting the battery life significantly.
Some early decisions imposed delimitations such as the adherence only to Android for
developing the prototype game and analysing only 4 different machine learning algorithms.
1.2 Research questions
The main research questions posed at the start of this work were as follows:
• How well can we induce greener transportation choices by persuasive games?
• What aspects of persuasive games are impactful on transportation choices?
• How can one identify specific forms of transport (car, bus, bike, walk, train, plane)
without manual input and without significantly reducing battery life?
The first question is answered by qualitative studies and having volunteers play a prototype
persuasive game. The second question is answered by qualitative studies from both the general
public, as well as testers of the prototype game. The third question is answered both by offline
analysis using the Weka 3 toolkit [5] as well as user-experience based qualitative studies.
Assuming the first and second questions are answered, persuasion via games could possibly be
deployed on larger scales to achieve change. Answering the last question is vital to this specific
scenario, where, without detecting transports, it is much harder to realize a convincing game.
8
1.3 Conduct of the experiment
This work was conducted with ethical approval from Leeds Beckett University’s Ethics
committee. All participants were informed how the data was to be used, and all data has been
anonymized before presentation. Mainly two forms of data gathering were used: online
questionnaires and data submitted automatically when playing the prototype game. Some
follow-up questions and interviews were used to gather further qualitative data from the game
testers.
The participants of the study were mainly recruited over social media via the author’s personal
account. Thus, most participants know the author either directly or in-directly (as the
recruitment posts may have been shared or disseminated further), and may have introduced bias
both within the transport sample gathering phase and game-testing phases.
The machine learning components were all conducted using the Weka toolkit [5]. For initial
offline analysis as well as for comparison studies, the version 3.8.2-Snapshot was used. For all
Android-related online and offline analysis a GUI-stripped port of the Weka 3 was used (Weka-
for-Android on GitHub) [14]. A maximum difference of 1% classification true-positives
difference was noticed between Weka’s pre-built Explorer application and our own offline
analysis software based on the Android-port.
1.4 Structure of the thesis
This report is structured as follows:
• The Introduction section provides an understanding of the reasons for and necessity of
the work described in this thesis.
• The Related Work covers various aspects relevant to the project, including Behaviour
change, Persuasive Design, and Transportation Mode Detection.
• The Theory section explains some of the intrinsics and details of machine learning,
game design and the psychological basis for persuasion.
• The Methodology section goes into detail of all aspects of the project. It dives into
details that are relevant for the design of the game, describes how the transportation
mode detection is implemented and tested, and describes the process for finding
volunteers to play the game and how the game is to be evaluated.
9
• The Results section includes descriptions, images and links for the prototype game,
results for the testing of the transportation mode detection algorithms, and results from
the testing of the game. For evaluation of the game, questionnaires before and after
playing are analyzed and presented. Some quantitative data is also presented on what
modes of transportation were used by the players throughout the test period.
• The Discussion section analyzes the presented results and discusses any short-comings
as far as intended results (reduction of motorized transport use), anomalies or bias of
data are concerned.
• The Conclusion presents a brief summary of what has been presented.
10
2 RELATED WORK
As described in the section 1.1, a persuasive game is developed and tested in order to change
human behaviour when it comes to modes of transportation. Since the game is designed to be a
persuasive game – wherein playing it will alter users’ behaviour – a study in persuasive games
and persuasive design in general is required. The first section on Persuasive Games largely
covers gamification, serious games, persuasive design and some modern examples.
The prototype game that is designed and tested aims to promote greener transportation via a
feedback-loop, where actions taken in the real world will affect outcomes within the game. To
analyze real-world actions taken by the users, transportation mode detection is implemented in
the game. Therefore, some related work in that field will be presented as well. The
Transportation Mode Detection section covers various contributions in the field that make use
of mobile-available sensors such as accelerometer, gyroscope and geolocational sensors.
2.1 Persuasive Games
Persuasive games, serious games and gamification are often aimed at health-related topics, such
as exercise and healthy eating, or promoting education and learning in general [15]. Some other
topics explored by persuasive games include smoking [16], views on homelessness [17], and
greening transportation [18].
Khaled et al. [16] discuss some of the difficulties in managing player attention, balancing the
game contents with reality, and questions concerning identity and target audiences, as these
impact the effects of persuasive games. Orji et al. [19] analyse persuasive games and target
players, and propose an approach to motivate players of certain gamer types with specific game
mechanics.
Deterding [20], shows in his presentations and publications a number of ways one can work
towards persuading users. Some examples include constraints (making the unwanted
impossible), default settings (to use the ‘path of least resistance’) and facilitation (easing change
somehow, e.g. by making behaviour change relevant data visible). He also argues that games
are good platforms for persuasive design as they are generally voluntary (already have intrinsic
motivators for players to play the games), are generally prestructured and have clear goals –
while still fostering interesting interactions. Extrinsic motivators such as money and grades are
11
generally proven to work well only in the short-term. For social multiplayer games, there are
also social motivators such as recognition, belongingness, cooperation, competition, etc.
Ferrara argues that serious games and gamification can cause real change, but highlights that
inattention to the quality of the player experience threatens its success [21]. In effect, he argues
that we should design games for change, rather than only applying specific gamification
elements and hope that they achieve the same effect that a whole game does.
The project by Froelich et al. to promote greener transportation [18] is interesting as it is one of
the few which has the same goal and setting as our work. In their work, they combined a self-
reporting system with a special pedometer and a dynamic graphic design to promote greener
transportation. Among the feedback participants gave, they suggested the use of negative
feedback as well as positive, to include more statistical figures of transport usage, and expressed
the discomfort of having to wear an extra sensor. The participants also appreciated visual
stimuli, but requested diversity over time (as it only featured linear positive graphical
progressions).
2.2 Transportation Mode Recognition
There are various approaches of transport recognition or classification. The relevant ones for
this project are those which are readily available or compatible with Smartphone based
approaches. Research conducted into distinguishing motorized transportation as one class from
all other modes of transportation has been mostly successful [22] [23]. It is when different
motorized transports are to be distinguished that more difficulties arise, but are usually dealt
with by using specific sensors targeting the given transport [24].
Activity recognition – which is a separate branch of machine learning targeting human-centered
activities – have been able to reach up to 90% classification accuracy for common classes
(sitting, lying down, walking, running) [25], or even higher rates for more classes if additional
sensors are used [26].
Accelerometer-only approaches have been largely successful to classify a limited amount of
motorized vehicles. For example, 97% classification accuracy for 3 classes (Car, Train,
Pedestrian) has been achieved using Support Vector Machines [27], and 80% classification
12
accuracy for classifying 6 modes of transportation (Walk, Bus, Train, Metro, Tram and Car)
has been achieved using a large number of features from the gathered data (78 features) [28].
Lorintiu and Vassilev proposed a model using both Random Forest and a Discrete Hidden
Markov Model for filtering for which they reached up to 94% accuracy. They used both
accelerometer and magnetometer data to identify 7 classes (still, walk, run, bike, road, rail,
plane, other) [29].
Jahangiri and Hesham adopted different supervised learning approaches to classify 5
transportation modes (car, bicycle, bus, walking, and running) [30]. Methods tested included
K-nearest Neighbour (KNN), support vector machines (SVMs) and Tree-based models
including Random Forest (RF). They used a total of 80 features extracted from four smartphone
sensors (Accelerometer, Gyroscope, GPS and Rotation Vector) to train their models and
managed to achieve classification accuracies of 91.2% for KNN, 94.6% for SVMs, 87.3% for
Decision Trees and 95.1% for a bagging and RF model.
Bedogni et al. proposed in their first paper [31] the use of so-called ‘magnitude’ values as well
as a time-based history set to filter out noise and improve classifier results. They reached an
initial 97.7% accuracy for 3 classes (walking, car, train). In their second contributing paper
[32], Bedogni et al. further evaluated their approach using 8 classes (standing, walking, driving,
train, bike, city bus, national bus), where they reached a mean accuracy of 79% for
Accelerometer-only, 87% for Accelerometer & Gyroscope, and 95% for using Accelerometer,
Gyroscope and Geolocational data all together.
13
3 UNDERLYING THEORIES
This section presents a brief introduction into both machine learning techniques as well as game
design so that the remaining sections may be better understood.
3.1 Machine Learning
Machine Learning is a subfield of computer science that tries to give computers the ability to
learn that which is not explicitly programmed. Being an evolution of studies in pattern
recognition and computational learning theory of artificial intelligence, machine learning
studies the construction of algorithms that can learn from and make predictions on sets of data
– so called data-driven analysis. It is often used where it is infeasible or difficult to create
explicit algorithms for e.g. filtering of e-mails, detecting a certain state in a complex system, or
computer vision. Crucial to machine learning is having enough training data available in order
to achieve any meaningful pattern recognition.
Machine learning systems are generally divided into three types of learning:
• Supervised, where the algorithm is presented a given set of inputs and their
corresponding outputs, and queried to build a model to map said inputs to the respective
outputs.
• Unsupervised, where the algorithm is presented a set of inputs, without corresponding
outputs, and tasked to find a structure within the input and divide it into some amount
of new outputs.
• Reinforced, where an algorithm or program is given a goal in a dynamic environment
and tasked to reach it, with rewards and punishments dealt out as it iteratively tries to
solve the problem.
All algorithms presented and tested in this thesis are supervised machine learning algorithms.
Before presenting the actual algorithms, introduction to some further concepts around machine
learning are required. It is worth noting that many of these algorithms and names may occur in
different versions. For example, Random Forest has been evolved a few times, and has several
parameters. Described in the following sections are the versions as they are implemented within
the Weka toolkit [5], which was used for all machine learning components of this thesis.
14
3.1.1 Machine Learning Definitions
An ensemble machine learning technique is a technique which makes use of several machine
learning classifiers to improve results over using only a single classifier.
Bootstrap aggregating or bagging, is an ensemble meta-algorithm designed to improve stability
and accuracy of machine learning techniques [33]. Given a specific training set D, m new
training sets are generated by randomly sampling from D. The random sampling allows
repetition, meaning that each new training set will hold approximately 63.2% of the unique
samples of D (with the rest being duplicates). Using the new training sets, m models are
generated, and their output is combined by averaging (for training) or voting (for predicting).
Bagging improves stability, helps with overfitting and is usually applied to decision trees.
Overfitting is the term when a classifier has become too complex and biased towards its training
set so that it will cause more classification errors during prediction on new datasets. Pruning
and bagging are two ways to counter overfitting.
Pruning is a machine learning technique that reduces the size of decision trees by removing
sections of the tree that hold little power to classify instances. This reduces the complexity of
the classifier and should improve predictive accuracy by reduction of overfitting.
Class, within machine learning refers to a specific label which a sample or set of data may have.
For example, a set of data with low activity might have the class ‘Idle’, and a set of data with
high activity might have the class ‘Walking’. The class is used for training machine learning
classifiers, and when a classifier is used for predicting it will produce a class depending on its
input data.
TP, or True-positive is a prediction that was correct.
FP or False-positive is a prediction which was false, and it in fact was another class.
Precision, or positive predictive rate, is a measure computed by the sum of True-positives
divided by the sum of True-positives and False-positives for a given class (TP / (TP + FP)).
Recall, or sensitivity, is a measure computed by the sum of all True-positives divided by the
sum of all positives for a given class (TP / all positives).
15
F-Measure, or the harmonic mean, is a combination of both Precision and Recall, see equation
1.
𝐹 = 2 × 𝑝𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 × 𝑟𝑒𝑐𝑎𝑙𝑙
𝑝𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛 + 𝑟𝑒𝑐𝑎𝑙𝑙 (1)
MCC, or Matthews correlation coefficient, is a measure of quality for binary classifications. It
takes into account true and false positives as well as negatives. An MCC of +1 represents a
perfect prediction rate, 0 random predictions, and a −1 represents 100% errors. It is sometimes
also known as the phi coefficient.
ROC Area, or Area under the ROC (Receiver operating characteristic) curve, can be interpreted
as a performance indicator of a classifier, and is often used to compare classifiers.
PRC Area, or Area under Precision-Recall Curve, is yet another indicator for the performance
of a given classifier.
3.1.2 Random Forest
Random Forest (or RF) is an ensemble machine learning technique, which makes use of a group
of decision trees in a specific manner to achieve better predictive performance than a lone
decision tree could achieve [34]. For each tree in the forest, a random vector is generated to
dictate how it should grow. Given an input 𝑥, each tree will cast a unit vote for the most popular
class. Random trees also use random elements to determine the number of and which features
to use for splitting each node.
Breiman [34] describes how a single tree classifier may be unable to handle a large amount of
input variables (e.g. a thousand variables for medical diagnosis and document retrieval), while
a forest grown on random features (a Random Forest) should improve accuracy.
Some characteristics of Random Forest include:
• Accuracy as good as contemporary classifiers, sometimes better.
• Relatively robust to outliers and noise.
• Faster than bagging or boosting.
• Gives useful internal estimates of error, strength, correlation and variable importance.
• It is simple and easily parallelized.
16
Since bagging is optional for Random Forests, another kind of random subset selection is used
when candidate trees are to be split in the learning process, sometimes called ”feature bagging”.
This is done as it should make the trees more correlated, thus increasing subsequent accuracy
during prediction.
3.1.3 Random Tree
The Random Tree (or RT) as implemented and used within the Weka toolkit [5] is described as
a tree that considers K randomly chosen attributes at each node, performs no pruning, and has
options for allowing estimation of class probabilities. In essence, Random Tree is the base
classifier or base learner used by RF within Weka.
3.1.4 Bayesian Network
A Bayesian Network (sometimes Bayes Network, abbreviated BN) is a probabilistic graphical
model used to represent knowledge about an uncertain domain [35]. Each node in the graph
represents a random variable, while the edges between the nodes represent probabilistic
dependencies among the corresponding random variables.
The BN implementation within Weka is based on the ADtree as described by Moore and Lee
[36], and uses the K2 search algorithm [37] [38]. The ADtree is a data structure intended to
minimize memory usage and accelerate BN structure finding algorithms, rule learning
algorithms, and feature selection algorithms while K2 is an algorithm for searching belief
networks to maximize the probability metric given by a chosen equation.
3.1.5 Naive Bayes
Naive Bayes classifiers (or NB) are a set of simple probabilistic classifiers based on applying
Bayes’ theorem with strong (naive) independence assumptions between the various features.
The Naive Bayesian classifier as implemented in Weka is based on the work by John and
Langley [39]. It uses estimator classes, where numeric estimator precision values are chosen
based on analysis of the given training data.
3.2 Game Design
Game design as such is the art of applying design and aesthetics to create a game for some
specific purpose – usually entertainment. Some related academic fields include gamification
(which revolves around applying game-design elements in non-game contexts), game studies
17
(the study of games, the act of playing them and cultures surrounding them) and game theory
(strategical decision-making).
Tracing back to research in the 1980s, Thomas W. Malone proposed heuristics for what makes
games fun to learn [40]. In his work, he largely categorized the characteristics of good games
or other enjoyable situations into three categories: challenge, fantasy and curiosity.
Another set of proposed heuristics are those presented by VandenBerghe [41] [42], named the
5 Domains of Play, or the 30 Facets of Play. These focus both on categorizing players, as well
as categorizing game mechanics and games, and could possibly link the players and their game
preferences. The 5 domains VandenBerghe presented are based on the Big 5 personality traits
(also known as the five factor model) [43], which consist of the following factors: openness to
experience, conscientiousness, extraversion, agreeableness, and neuroticism. VandenBerghe
refines these Big 5 personality traits into the following categories that can be used in the context
of games, game mechanics and gamer-types:
• Novelty, which distinguishes open, imaginative experiences from repetitive,
conventional ones
• Challenges, which deals with how much effort and/or self-control the player is expected
to use
• Stimulation, which deals with the stimulation level and social engagement of play
• Harmony, which reflects the rules of player-to-player interactions
• Threat, which reflects the game’s capacity to trigger negative emotions in the player.
One popular profiling system described by Bartle categorizes players into four main categories:
Achievers, Explorers, Socializers and Killers [44]. Achievers are those who focus on setting
and accomplishing their own goals within the game, Explorers try to find out as much as
possible about the game itself, Socializers focus on role-playing or casual text interaction with
other players, and Killers use actions within the game to cause distress to (or, rarely, help) other
players.
18
Table 1 gives a brief overview of those elements covered by VandenBerghe and how they could
be mapped onto the heuristics described by both Malone and the player types categorized by
Bartle. Obviously, the Stimulation and Harmony parts – which represent the various social and
player-to-player interactions are more or less lacking within Malone’s initial proposal, while
the Novelty part is not covered at all by the Bartle profiles. Note also that this is a very simplified
comparison, since the work by VandenBerghe presented a total of 30 characteristics. For the
sake of brevity, VandenBerghe’s work is not further analysed in this work.
3.2.1 Challenge
A goal is almost required for a game to be called as such. Some recommendations on goals are
as follows:
• For simple games, a goal should be obvious and compelling. This can be done via visual
effects (Breakout) or fantasy (Hangman).
• A game can also be without goals, but then the game needs to be well-designed so that
users can generate their own goals (that should be appropriate to their skill or difficulty
level).
• The best goals are often practical or fantasy goals (e.g. reaching the moon in a rocket).
• The players must be able to tell if they are getting closer to the goal. This could be done
via some visual or aural stimuli.
One topic relating to the Challenge-aspect of game design is self-esteem, since it is highly
correlated with the players’ successes and failures within the game. It is thus best to consider
this when designing the level of challenge within games. If failures are sufficiently severe to
lower a person's self-esteem, it will also decrease their desire to play the game. Two
implications from this are that games are recommended to use variable difficulty levels, and
VandenBerghe
domain
Malone counterpart Bartle profile
counterpart
Novelty Fantasy -
Challenge Challenge Achiever
Stimulation - Explorer
Harmony - Socializer
Threat Challenge Killer
Table 1, Comparison between VandenBerghe and Malone’s heuristics
19
that perhaps the performance feedback should be presented in a way that minimizes possible
damage to the player's self-esteem.
3.2.2 Uncertainty
Another typical requirement for good games is uncertainty. If the player knows they will win
or lose, the gaming experience will be boring. Some steps to ensure uncertainty are as follows:
• Variable difficulty levels
• Hidden information – which increases difficulty and provokes curiosity
• Randomness – which can be used to increase uncertainty in almost any game
• Multiplayer interactions – including multiplayer interaction will likely add more
uncertainty to a game.
3.2.3 Fantasy
Fantasy often makes games more interesting, and involves objects, environments and situations
which are impossible from a realistic point of view.
Fantasy may be described in two versions: extrinsic and intrinsic. The extrinsic fantasies are
those where real-world actions (e.g. solving arithmetic problems) which progress the game,
while intrinsic fantasies are those actions which occur within the game itself that progress the
game. Intrinsic fantasies may be more interesting, immersive and instructional than extrinsic
fantasies, since they better incorporate the sense of realism within the game (in-game actions
affecting the in-game world).
Consider, for example, the logic where solving an arithmetic problem in the real world would
yield a change within the game world. This could work, but possibly only for a narrow range
of scenarios (e.g. inventing or crafting something within a game) without breaking the
immersion of the game.
''It is very difficult to know what emotional needs people have and how these
needs might be partially met by computer games. It seems fair to say, however,
that computer games that embody emotionally-involving fantasies like war,
destruction, and competition are likely to be more popular than those with less
emotional fantasies.'' – T. W. Malone [40]
20
When studying the modern-day emerging augmented reality games and apps, perhaps the
extrinsic fantasies will appropriate larger use in digital games. Take for example Pokémon Go,
where moving about in the real world is required to progress the game [45].
3.2.4 Curiosity
Curiosity is another important component of game design. It may be independent of goals and
fantasies, but may also be stimulated by the game environments, or the complexity of the game.
Just like in movies, you may be given clues as to where the story will end up, or what will be
revealed, and you may have your curiosity satiated once it is finally revealed. These kind of
storytelling scenarios are present in games as well.
Curiosity can be divided into two types: sensory and cognitive curiosity.
Sensory curiosity
Sensory curiosity basically entails changes in sound or graphics, and can be measured in
'technical events per minute', such as changing camera angles, playing a sound effect,
displaying a graphical reward, etc. Sensory events can be used as a decorative piece
(background animation or music), to enhance fantasy (by evoking some certain thoughts or
feelings), as rewards ("Good job!", "Congratulations!", etc.), or as representation systems (e.g.
audio feedback on event occurrences, using graphical elements instead of text). Using sensory
events as rewards can increase the sense of completion, but can also become tedious or
undermine people's interest if used incessantly.
Cognitive curiosity & Informative feedback
Cognitive curiosity can be thought of as wanting to improve, solidify or verify one’s own
knowledge about some knowledge structure. In games, this could be verifying your own skill
level, recalling if you can traverse some game area without the help of a map, or testing your
own limits to what you can achieve within the game in order to better understand the game
itself.
Malone claims that people are motivated to achieve completeness, consistency and parsimony
for to all their cognitive structures [40]. He continues to argue that the way to engage in players’
curiosity is to present them just enough information to render their current knowledge seem
incomplete, inconsistent or unparsimonious. The learners (or players) are then motivated to try
and learn more and improve their cognitive structures accordingly. For example, reading a
21
crime novel’s last chapter and figuring out who the murderer was brings completeness to the
knowledge structure you had of that specific story.
22
4 METHODOLOGY
The methodology is largely split into three parts. The design, testing and implementation of a
persuasive game, methods for evaluation of the promotion of green transportation when
deploying the developed game, and the design and testing of an approach for transportation
mode detection to be used within the game.
4.1 Persuasive Game Development
In order to develop a persuasive game, the full procedure of developing a digital game has to
be considered. The first few subsections (4.1.1 to 4.1.3) present the system architecture for the
game and its peripheral systems, the persuasive-related requirements of the game, and a list of
applications that were developed as part of the project. The remaining subsections (4.1.4 to
4.1.8) discuss some aspects of the game and some decisions that were taken during game
development, as well as rationale to justify decisions made.
4.1.1 System Architecture
For this project, a series of applications were developed, with an accelerometer sampler
application and a persuasive game being the two applications used or tested by volunteers. The
sampler application was named Transportation Mode Sampler, as it included categorization of
sampling data to the target transport modes and was used by volunteers to help gather data for
transportation classification tests. The serious persuasive game Evergreen was named as such
since it refers to the evergreen-trees as a symbol of sustainability, and it also gives a good
picture of what the game is about – surviving out in the wilderness against forest beasts.
23
Figure 4 gives a glimpse into how the system was laid out code-wise within the scope of this
thesis. Section 4.1.3 lists all applications developed as part of this thesis.
4.1.2 Persuasive Game Requirements
Initial requirements for the project highlighted that players of the persuasive game should be
motivated to change their current behaviour. For a game to be successful it also requires good
game design. The initial game design requirements could thus be listed as follows:
• Iterative game design so it can be played for longer periods of time
• Include multiplayer interactions to make it more appealing
• Feedback-loop based on user data to incentivise behaviour change
Additional requirements were derived from the inclusion of a feedback loop, since Machine
Learning was chosen as a method to accomplish it:
• Samples gathering to train and test classifiers for usage
• Classifier testing to evaluate which one to use, and in what way
Figure 4, System architecture overview
24
According to the characterization method proposed by Michie et al [46] the game design
requirements related to persuasiveness could be categorized into categories shown in Table 2.
The iterative game design and character-development typically used in role-playing games
could be considered as Incentivisation where the game creates an expectation of grander
rewards which increases with play. The multiplayer interactions could both alter the
environment (in the form of social context of players within the game) and could also –
according to the modelling intervention – create models of people or teams within the game
world to which players can imitate or be inspired (either via player-player interaction or via
public green transportation activity leader boards). The feedback-loop could be categorized as
persuasion in the sense that it could induce positive and/or negative feelings, and thus could
also be considered Incentivisation (expectation of reward) as well as Coercion (expectation of
punishment or cost) depending on mode of transportation.
4.1.3 Applications developed
In terms of separate applications developed, the following were planned and then
implemented:
• Persuasive game, entitled Evergreen
• Transportation Mode Sampler – an application for gathering data samples
• Transport Detection Service – an Android service to detect mode of transportation used
• Evergreen game server – Java-based back-end for co-ordinating the multiplayer game
mode
• Java-classes for training, testing and evaluating preliminary data and classifier
accuracies (WekaManager, WClassifier, etc) based on the Weka API [5].
Requirements Rationale Behaviour intervention
categorization
Iterative game design Allows for longer periods of play – should
foster greater behavioural change
Incentivisation
Multiplayer interactions Make change more likely by increasing
the game’s appeal
Environmental Restructuring,
Modelling
Feedback-loop to
incentivise behaviour
Giving consequences for real-life actions
in the game should incentivise change
Persuasion, Incentivisation,
Coercion
Table 2, Requirements, their rationale and categorization.
25
4.1.4 Game Genre
For game genre, a turn-based strategy and role-playing game hybrid was chosen. There are
several reasons for this. Firstly, it enables an iterative approach to try and persuade players for
each turn or day that they are playing the game. Secondly, players of role-playing games tend
to play them for a long time, as long as they are well-designed. In the game, each turn would
correspond to one real-life day. Actions in the real life (transports taken) would affect, to some
extent, results in the game, and thus, give an incentive for players to subsequently choose
greener modes of transportation. Using a turn-based approach also makes it available to a larger
audience, as less time is required to play it (a few minutes per turn or day), whereas a real-time
game may distract and interfere with daily life. Pokémon Go is a great comparison as it is also
in the same genre, gathered a large popularity, caused a distinct change in behavioural patterns
of players, but also has its disadvantages and hazards inherent in the game design [45].
4.1.5 Game Goals
Since a goal of this work was the design of a persuasive game – a game whose goal is not
primarily (or exclusively) for entertainment – several goals would be present within it
concurrently:
• Reduce emissions by choosing greener forms of transportation.
• Promoting awareness of each person's environmental footprint.
• Defeating other players or surviving the longest.
To keep the game compelling, the first and second goals are embedded in the game and are not
explicit goals for the players. They are instead tools and parameters in the game which players
can try and use to achieve the third goal. Within the resulting game, these goals are mainly
integrated into a generation of random events which are spawned depending on which
transportation mode players use, as well as one of the main game statistics called “Emissions”.
The third goal is a typical game-goal that resonates well with general and contemporary game
designs in that it is likely to provoke emotions and is more likely to entice game players. Within
the game, the players may also set their own goals – such as helping others, building the largest
shelter, etc. Due to the complexity of the resulting game (and role-playing games in general),
players tend to set up different own goals based on what they enjoy in games.
26
4.1.6 Game Fantasy
Through intrinsic fantasy, the player can choose a wide array of actions within a conflict-ridden
fantasy-world. Through extrinsic fantasy, players' real-life actions will be used in a feedback-
loop manner back into the game, stimulating transportation choice. This way, the game will
permeate players’ everyday lives, possibly generating a larger behavioural change – which is
the aim of this game.
As discussed in section 3.2.3, people have different emotional demands, and may thus find
different forms of fantasies appealing. In order to appeal to at least one group of players, the
genre of the game and most of the mechanics have already been decided: post-apocalypse where
nature is out to get you. Common game mechanics from turn-based strategy and role-playing
games were chosen, as they best fit in with the designed player experience and projected playing
time required for behavioural change. The required estimated time for signs of change is at least
7 to 14 days. One earlier hypothesis was that some groups of people enjoy this genre, and may
thus enjoy the game, while others may reject it.
4.1.7 Game Curiosity
As described in section 3.2.4, the game should be novel with an element of surprise to some
extent, but should not be too complex so as to deter players. Some expectations should also be
met (adhering to certain common game mechanics and interactions), while some parts should
be novel coupled with uncertainty (new game mechanics or new interpretations of existing
ones) in order to appeal to a wider audience.
Based on the above, the game abides by some common rules and game mechanics found in
modern turn-based role-playing games (RPGs) and strategy games. The game also features new
game mechanics to make it novel and invoke curiosity as well as fulfil the requirements for
being a persuasive game (here defined as stimulating behaviour change regarding vehicle use).
As for sensory curiosity, the game is designed to give more extensive sensory events as rewards
when noteworthy events happen within the game. For example, the player’s dwelling graphics
updates as it is upgraded, and the background picture is tinted into different shades based on
how points of emissions the player has emitted. In the beginning of the game, the player has 0
emissions and has a nice and soft green background. As emissions increase beyond a certain
threshold, yellow tints at the bottom appear. At the later stages, the tints gradually change to
orange, red, and lastly, black. At each progression, the “decaying” colours also gradually move
27
upwards, so that the entire screen at the end of the game may be a dark red and black gradient.
Figure 5 shows the progression as it was implemented in the Android prototype game.
Daily events occurring in the game would not get any special sensory events besides
presentation in a summarized form, while there were plans to give some further sensor feedback
for more notable events (such as surviving a harsh encounter with dangerous foes).
Unfortunately, further sensor events were not added, but may be incorporated in a later version.
4.1.8 Game Design details
In the developed game, daily actions are chosen, such as gathering food or resources, inventing
and crafting weapons, armour and tools, building defences, scouting, interacting with other
players, etc. The daily actions are then used as inputs for the game once each new day or turn
is simulated. Skills are also chosen by players to be trained so that they may specialize and
become better in one trade or another, to try and motivate cooperation. Some actions and skills
were also competitive, such as stealing from or being able to attack other players. Active actions
such as sending resources, items or messages between players could be performed on demand
to allow some flexibility.
Within the game, there are some relevant statistics, with emissions being the next-most
important one (affecting overall game difficulty) besides hit points (the standard statistic used
to represent a character’s vitality in many role-playing games). Different modes of transport
give varying amounts of bonuses to the in-game Daily actions, as well as generate various
amounts of emissions. Choosing specific actions within the game which consume resources
(crafting, inventing, building defences) also increase the emissions statistics, while some
actions and skills actively reduce or indirectly reduce current or future emissions generation.
Figure 5, Sequence of background images as emissions increase
28
To adhere to good game-development and software development practices, the development
lifecycle was preceded with the development and evaluation of a paper prototype (see appendix
1) [47]. Volunteers were recruited and the game was tested in group sizes between one and
three. Four separate groups tested the game for initial feedback and iterations. Testers of the
paper prototype found the game interesting, after which a digital graphical prototype was
designed (see Figure 6 or Appendix 2).
Using volunteer testers and the help of a graphics artist, an Android-based version of the game
was developed. Figure 7 shows some screenshots of the game as it was published in social
media (Appendix 3 shows more screenshots from the tested game version).
To readers who intend to analyse the game in further detail, we suggest reading Appendix 1
(since the paper prototype game design largely corresponds to the design used within the
developed Android prototype).
4.2 Evaluating Behaviour Change
To evaluate potential behaviour change, one expectations questionnaire, as well as pre- and
post-intervention questionnaires were given out to volunteers. The expectations questionnaire
was distributed before any serious development of the game began, the pre-intervention
questionnaire was distributed before testing began, and the post-intervention questionnaire was
given to players after they had played the game for 10 days or more. Both quantitative and
Figure 6, Early design stages of the persuasive game titled Evergreen. Far left: First page of the initial paper prototype (11 pages in total). Middle-left: Early design of the game’s splash-screen. Middle-right: early design of the game’s main screen showing player statistics in the top, buttons for actions and a log of what has happened previously. Far right: early design of the results-screen, which is presented after each new day.
Figure 7. Screenshots from the Android version of the game Evergreen. Far left: splash-screen. Middle-left: Main screen, showing statistics in the top 6 icons. The background changes colour as emissions increase, and the representation of the shelter changes as it is being upgraded. Middle-right: ‘Daily Actions’ selection screen. Far-right: the results-screen showing what has happened the most recent days/turns.
29
qualitative answers for each respondent was recorded, and participating game testers were also
asked follow-up questions based on their playing experience. Volunteers and participants for
testing the game were mainly recruited over social media with no extra incentive added to play
the game.
4.3 Gathering sensor samples
Volunteers were sought out to assist in providing training data. A small app was developed
where users could observe current data, see the preliminary window feature values and export
the data into other applications (see Figure 8). Volunteers were sought out in the vicinity both
locally and online, and for each transport the aim was to include an equivalent amount of
samples, comprising at least 30 minutes’ worth of sampling. If classification errors were found
early during testing, further samples were gathered to improve classification for that specific
transport scenario. In order to make the final trained transport-classifier user independent,
samples were requested from at least 2 volunteers per transport whenever possible.
30
4.4 Transportation Mode Detection
The transportation mode detection work that is
presented and analysed in this work is based
primarily on the work presented by L. Bedogni
et al [31] [32]. Accelerometer- and Gyroscope
data was queried at 20Hz, and saved in intervals
of non-overlapping 5 second duration windows.
Depending on what applications were running in
the background, the number of samples that were
gathered have been higher, as this is how the
Android OS handles sensor requests. If the
system supplied samples at higher rates, no data
would be discarded, so some intervals could
differ in their actual sampling rate.
Each sample within the time window was
recalculated into a magnitude value to make the
sample data user orientation- and position-
independent (see equation 2).
Based on a set of magnitude values, each interval, minimum, maximum, average and standard
deviation values were calculated. These 4 values per sensor (8 in total) made up the time
window features that were later used for machine learning classifier training and prediction
tests.
To train the classifiers, data was gathered with the help of volunteers for 9 transportation modes
(10 including Idle): Bus, Foot, Car, Bike, Train, Tram, Subway, Boat, and Plane.
Each instance fed to the classifiers for training consisted of the 8 time window features
mentioned above, along with a pre-labelled transport (that was used to gather and calculate the
𝑚𝑎𝑔𝑛𝑖𝑡𝑢𝑑𝑒 = √𝑠𝑎𝑚𝑝𝑙𝑒𝑥2 + 𝑠𝑎𝑚𝑝𝑙𝑒𝑦
2 + 𝑠𝑎𝑚𝑝𝑙𝑒𝑧2 (2)
Figure 8, Screenshot of the Transport Data Sampler application volunteers used to submit data for the project.
31
previously mentioned features). During prediction, the classifier would then be fed 8 other
window features and queried to predict which transport was currently being used.
4.4.1 Noise reduction by using a History set
To improve prediction, a history set is used to filter out noise in the classifier predictions. As
an example, consider the following prediction sequence: Bike, Bike, Bus, Bike, Bike. It is
unlikely that a user would take a bus for a few seconds while all other predictions, before and
after, indicate that the user is riding a bike. Figure 9 visualizes how the history set would work
be used.
The usage of the history set of size N is as follows: when a new prediction is made, it is added
to the history set. If the set has more than N predictions, the oldest prediction is discarded. The
transport of highest frequency within the set is returned and used instead of the initial prediction.
Figure 9, How the History set can remove noise. It is improbable that the user switches transport for only 5 seconds (1 interval)
32
4.4.2 Sleep sessions
Due to the popularity of the game Pokémon Go, the associated effects of battery life degradation
from its use and the similarity in augmented reality with the Evergreen game we are working
on, the effects of introducing sleep sessions in-between samplings was also of interest. The
expected effects on accuracy is a degradation, but it is of interest as it could be used to plan
how much the resulting application will drain the user device's battery. The aim is to figure out
approximately how much time the transport detection service can sleep while still retaining a
certain classification accuracy, and this was not covered by other authors in previous works.
Initial approaches to use the history set together with sleep settings are visualized in Figure 10
and Figure 11.
Figure 10, The History set in combination with sleep sessions
33
In order to maintain the battery performance during testing, the sensor sampling service within
the resulting game used an alternating sleep schedule to reduce energy consumption. The
qualitative tests (using machine learning within the game) generally included sleeping using a
1:1 ratio of sensing and sleeping (e.g. sampling for 2 minutes, then sleeping for 2 minutes). This
is the same kind of method as shown in Figure 11. Figure 12 depicts the relationship between
the increased rate of errors and increase in sleep sessions. The errors generally occur at
increased rates right after the user changes transportation mode.
4.4.3 Gravity measurement miscalibration
After initial positive tests on classifier accuracy, a real-life test was carried out with the same
classifier integrated into the game. Due to the number of errors that emerged, we hypothesized
that the device orientation somehow still impacted the transport recognition. Brief tests showed
that the total gravity sensed varied with each device and orientation, which would in turn affect
all machine learning classifier results including the accelerometer (see Table 4 in section 5.4).
Figure 11, The History set in combination with sleep sessions, alternate approach
34
In order to ensure that the whole procedure and data were thoroughly device- and orientation-
independent and remove the effect of sensor-axis miscalibration, normalization of acceleration
values was applied to the minimum, maximum and averages of the acceleration sensor
magnitude values. This was done by dividing them all with the average value, thus centering
them on 1.0 instead of whichever value the specific device was calibrated to.
Figure 12, Increase in errors as sleep sessions increase
35
5 RESULTS
The results are divided into the following sections:
• game design, where an analysis is done on respondents’ answers to an initial
expectations-questionnaire as well as a questionnaire given to all who would test the
game.
• game evaluation, where an analysis is done on the qualitative feedback provided by
testers of the game as to its persuasive effects and limitations,
• transportation mode data sampling, where results of data sampling is shown and as well
as an investigation into the effects of device orientation on sampled gravity
measurements is shown,
• transportation mode detection, where results are shown of the various tests on the
gathered data, including n-fold cross-validation, the use of a history set to filter noise,
and results for when input data has had its acceleration values normalized.
The game that was developed is a persuasive game called Assaults of the Evergreen or just
Evergreen. Its official Facebook page with links to some relevant questionnaires can be found
here: https://www.facebook.com/AssaultsOfTheEvergreen/
5.1 Game design
To get an idea of how a game should or could be designed, as well as to assess the viability of
a persuasive game’s effects on people, two primary surveys were conducted. The first
“expectations”-questionnaire was disseminated in January 2017, and the second “pre-testing”
survey was disseminated in April 2017. The first ”expectations”-questionnaire received more
than 40 respondents, and the second ”pre-testing” questionnaire received 24 respondents.
Respondents for the initial ”expectations”-questionnaire were asked to which extent they
thought a game could impact their lifestyle, if they were willing to play a game designed to
improve their daily choice of transportation, and asked how they would imagine such a game
would look like or be designed. A majority of the respondents had a background of playing
digital games (Smartphone, Console or PC), and were of the opinion that games can have some
impact on their lifestyles. Figure 13 shows response distribution for one of the questions, where
1 was labelled ‘Not at all’ and 5 was labelled ‘A lot’.
36
Responses to an open free-text question concerning how a persuasive game would be designed
were diverse. Respondents suggested features such as showing real-life data and personal
statistics, adapting to players’ personal schedules, and using notifications and achievements.
Among the concerns were battery life, privacy of collected data (e.g. locational), and that the
game does not demand too much time from players. Some respondents said they would play
any game if it was fun, while others stated that they would not play the game to improve their
daily choices since they were already using the greenest modes of transport (walking or biking).
Some respondents also highlighted the social aspects, including competitions, and leader boards
that may motivate players. One respondent mentioned that they would be more interested in
features that help them choose greener modes of transport for a specific journey.
When asked how successful a persuasive game could be concerning transportation, some
respondents perceived the choice of transport is mostly one of practical nature: some distances
and journeys are just not practical with greener modes of transport. One respondent recalled a
long-term biking contest that was held at their workplace on a regular basis (weekly, monthly,
yearly), and described that people participated mostly because of the competition (as part of the
Figure 13, Expectations of how much a game can impact respondents’ lifestyles
” Not at all ” ” A lot ”
Response fre
quency
Figure 14, Population distribution of the Pre-Testing questionnaire (Sex, Age, Occupation)
37
gamification) even though the website of the leader board was not very good. One respondent
mentioned that even if the game is just entertainment for some players, it may encourage others
to contemplate changes in their lifestyle. One respondent likened the concept to the success of
Pokémon Go, claiming that it could be successful only by looking at how that game made
players walk around everywhere. Some respondents mentioned that it all depends on the quality
of the game and the marketing strategy: that any game can be successful if marketed well.
For the “pre-testing” questionnaire, respondents were asked in more detail who they are and
their current habits. There were 24 respondents to this questionnaire. The respondent’s
distribution regarding to sex, age and occupation is displayed in Figure 14. In total 15 men and
9 women responded, of varying ages with the 26-35 interval being the most common age-group.
11 were working full-time and 10 were students. 11 were recruited personally by the author,
while 13 were recommended to try out the game by a friend.
Similar to the results in the initial expectations-questionnaire, respondents of the pre-testing
questionnaire had an overall positive view of the potential effects of a persuasive game such as
Evergreen, as can be seen in Figure 15. When responding to the question, the value 1 was
labelled as ‘No’ and 5 as ‘Yes’, with respondents left to interpret the values in-between
themselves.
Details for the Expectations- and Pre-testing questionnaires can be viewed in Appendix 8 and
9 respectively.
5.2 Game Evaluation and persuasive effects
The game had 4 testers who played the game in multiplayer mode for at least 10 days. Two out
of 4 players were still playing 50 days after launch. The four testers that played the game for at
least 10 days each spent either 1-5 minutes or 6-10 minutes a day playing the game, and a
similar amount of time talking about it with friends, colleagues or others. They generally
thought the game was well-designed and well thought out, that it was generally not too hard to
understand and play, and that it had enough character customization. Similarly, the testers
generally thought the game had well-designed graphics that made it easy to understand what
was happening in the game and enjoyed playing the game.
38
Some criticism from the players included a lack of players to interact with and a lack of a proper
tutorial. One player suggested that a more significant decrease of emissions should be added if
the player was indeed walking or biking, and that there was too vague of a connection between
transports chosen in the real world with consequences in-game. One player also suggested it
needs more “in-your-face” pop-ups used in contemporary smartphone games.
Some players expressed a desire for more features in the game, that they wanted to play it more
than the few minutes spent each day to decide their daily actions. One suggestion here included
Start and Stop-buttons for walks or bike sessions (the green transports) with a selected desired
outcome – a bonus of some sort. For example, player A wants to gather berries within the game.
The player then activates an active foraging session within the game that verifies that the player
is indeed currently walking. After walking for some prescribed time, player A stops walking,
and requests a confirmation of what was obtained during the walking session. Depending on
the length of the session, player A may obtain an increasing amount of food points representing
the berries gathered within the game world (e.g. 1 point of food for each 5, 10 or 15 minutes of
walking could be tested). One player who suggested this game mechanic and also mentioned
that it would help them go for walks more often, presumably due to the immediate feedback
(the game would only give results every 24 hours otherwise), and that it would help their
wellbeing as well (since the green transports recognized within the game generally require
exercising).
Most players felt that their choice of transport was influenced to some extent while playing the
game, where half of participants tried walking more than before, and one tried to drive cars less
Figure 15. Respondents views on the potential success of persuasive games. ” Yes ” ” No ”
Response fre
quency
39
than before. When asked how much of their total traveling time was influenced, the answers
were 0%, 5%, 10%, and 25% of total travelling time respectively between testers.
When asked why they were not influenced and what would have had an influence on their
choices, one mentioned that the effects of actual transport did not really feel like it was reflected
in the game. Another tester stated that while it made them more aware of their actions, other
factors stood out to be more important (distance, weather, time, etc). One participant mentioned
that they need a car to get anywhere due to where they live, but that if they had lived closer to
a city they would have walked or tried taking busses more often. Some further details for the
evaluative questionnaire can be viewed in Appendix 10, and full transcripts of all player
questions and followed up conversations can be read in Appendix 11.
5.3 Transportation Mode Data Sampling
For data gathering, a total of 21’096 time window features (or samples) were gathered,
corresponding to 29 hours and 18 minutes of data, divided into the transport classes depicted in
Table 3. To justify the need of acceleration sample normalization, some brief data on Android
device orientation gravity measurements are presented in Table 4. The columns represent
different volunteers’ respective devices, with standard deviations presented both on a per-
device and per-orientation basis. Note the increased deviations for the Face right and Face left
orientations, which are common for devices placed in pants’ pockets while sitting.
Transport
class
No
Samples
Corresponding
Time
Idle 2600 3h 37m
Bus 3327 4h 37m
Foot 1704 2h 22m
Car 3813 5h 18m
Bike 863 1h 12m
Train 2689 3h 44m
Tram 1309 1h 49m
Subway 444 0h 37m
Boat 1274 1h 46m
Plane 3073 4h 16m
Total 21096 29h 18m
Table 3, Breakdown of collected Transport data and corresponding time.
40
5.4 Offline Transportation Mode Detection
Initial classifier results using 10-fold cross-validation and 2-fold cross-validation using the
using Random Forest, Random Tree, Bayesian Network and Naïve Bayes classifiers are
presented in in the first 3 columns of Table 5. In the 4th and 5th column of Table 5 are the
corresponding results for 10- and 2-fold cross-validation using the normalized accelerometer
values (to ensure device and orientation ambiguity).
Table 6 presents the details of classification for each class when performing the 10-fold cross-
validation using Random Forest (RF) as printed within the Weka explorer. See section 3.1.1
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0,686 0,024 0,799 0,686 0,738 0,707 0,944 0,827 Idle
0,650 0,085 0,590 0,650 0,618 0,544 0,899 0,688 Bus
0,759 0,023 0,745 0,759 0,752 0,730 0,967 0,837 Foot
0,681 0,082 0,647 0,681 0,664 0,587 0,916 0,761 Car
0,684 0,012 0,707 0,684 0,695 0,683 0,970 0,763 Bike
0,604 0,061 0,593 0,604 0,598 0,539 0,915 0,633 Train
0,508 0,032 0,516 0,508 0,512 0,480 0,925 0,587 Tram
0,288 0,006 0,520 0,288 0,371 0,378 0,904 0,365 Subway
0,759 0,026 0,648 0,759 0,699 0,681 0,975 0,746 Boat
0,707 0,037 0,765 0,707 0,735 0,692 0,938 0,813 Plane
Table 6, Detailed results by class.
Orientations A B C D E F G Stddev Standing 9.867 9.945 9.935 9.844 9.808 9.755 9.817 0.063 Face-up 9.728 9.946 9.837 9.810 9.842 9.957 9.417 0.169 Face-down 9.699 9.926 9.677 9.812 9.826 10.086 9.962 0.135 Face right 8.532 9.794 10.226 9.807 9.641 9.640 9.897 0.491 Face left 10.748 10.038 8.976 9.875 9.751 10.156 9.873 0.489 Upside-down 9.684 9.964 9.361 9.818 9.787 10.028 9.319 0.255 Stddev 0.706 0.080 0.444 0.027 0.073 0.200 0.274
Table 4, Gravity measurements for sample Android devices and 6 different orientations.
Classifier 10-fold 2-fold 10-fold
NA
2-fold
NA
RF 67% 65% 53% 51%
RT 56% 54% 43% 41%
BN 48% 48% 41% 40%
NB 29% 29% 25% 25%
Table 5, Classifier results using 10- and 2-fold cross-validation, without normalized accelerometer values, and with normalized
accelerometer values (NA).
41
Machine Learning Definitions for descriptions of each column if you are unfamiliar with the
abbreviations.
Table 7 presents the confusion matrix as well as True-positive percentage rates (on the right-
hand side) when analysed within our own test-suite (10-fold cross-validation, RF). Some
differences in TP rate can be observed between the results run within the Weka Explorer
software compared to our own test suite (compare Table 6 and Table 7). Most classes show
near-equal results (<1% difference), with the exceptions of Bike (1.1%), Train (1%), and Plane
(3%).
Table 8 shows the results when using 10-fold cross-validation, while Table 9 shows the results
using 2-fold cross-validation. Both tables present the classification results of the chosen
classifiers using different sizes of the history set. Percentages displayed are the true-positive
rates when using the history set size stated in the top row (0 to 50). Highlighted are those results
where the classification rate reached its highest point for that classifier.
Classifier HSS 0 HSS 10 HSS 20 HSS 30 HSS 40 HSS 50
Random Forest 67% 73% 55% 42% 35% 23%
Random Tree 56% 69% 54% 42% 31% 24% Bayesian Network 48% 58% 48% 37% 28% 21%
Naïve Bayesian 29% 28% 24% 19% 16% 14%
Table 8, Classifier results when using 10-fold cross-validation for different history set sizes (HSS).
Classifier HSS 0 HSS 10 HSS 20 HSS 30 HSS 40 HSS 50
Random Forest 65% 93% 95% 95% 94% 93%
Random Tree 54% 89% 91% 93% 94% 94% Bayesian Network 48% 73% 78% 79% 79% 79%
Naïve Bayesian 29% 34% 36% 37% 38% 38%
Table 9, Classifier results when using 2-fold cross-validation for different history set sizes (HSS) with normalized accelerometer values.
Predicted values in each column, True values in each row.
a b c d e f g h i j
1786 166 107 112 30 50 61 28 164 96 | a - TP 68,7 Idle
80 2348 67 403 38 268 151 15 76 128 | b - TP 65,7 Bus
75 94 1290 47 67 14 37 11 35 34 | c - TP 75,7 Foot
60 395 51 2593 57 342 143 9 53 110 | d - TP 68,0 Car
29 25 107 64 600 6 23 1 2 6 | e - TP 69,5 Bike
31 280 23 281 5 1651 99 32 74 213 | f - TP 61,4 Train
21 179 31 228 18 108 653 3 63 5 | g - TP 49,9 Tram
40 123 21 23 2 47 24 127 28 9 | h - TP 28,6 Subway
42 99 14 31 0 68 49 4 956 11 | i - TP 75,0 Boat
71 161 22 177 20 229 22 6 36 2082 | j - TP 73,7 Plane
Table 7, Confusion matrix for the classes
42
As can be seen when comparing the tables, 10-fold cross-validation has an initially higher
accuracy rate (+2% for RF and RT), while the 2-fold cross-validation achieves higher accuracy
at larger history set sizes (HSS) since the amount of data it is tested upon is larger. This is due
to the nature of how the history set works, where the bigger the test size is, the higher chances
the history set will yield increases in performance.
Table 10 presents the confusion matrix for the best performing offline-results (2-fold cross-
validation, HSS 20). Note that almost all classes have now reached over 95% classification TP
rate, with the exception of Subway (which was under-sampled and is mistakenly identified as
Bus) and Tram (which was also relatively under-sampled and being mistakenly classified as
Bus or Car).
The performance of all classifiers are lower than those results presented by Bedogni et al, but
the same ranking of classifiers is shown, where RF performs best, followed by RT, BN and NB
(84%, 80%, 78% and 54% accordingly in their results) [32]. Some possible reasons for the
lower accuracy rates are less samples for training and testing (roughly half), less total time for
the corresponding samples (each sample recorded by Bedogni et al was an average of 10
seconds vs our 5 seconds), and the increased number of classes (10 instead of 7).
Using normalized accelerometer values the accuracy rates generally decrease, reaching at most
65% accuracy for HSS 10 in the 10-fold cross-validation, and 87% accuracy for HSS 30 and
40 in the 2-fold cross-validation (–8% accuracy compared to the displayed 73% and 95%).
Table 11 shows the confusion matrix for the best results when using normalized acceleration
values (2-fold cross-validation, RF, HSS 30). Most transports have TP rates above 90%, with
Predicted values in each column, True values in each row.
a b c d e f g h i j
2568 6 0 0 0 18 0 8 0 0 a - TP 98,8 Idle
0 3497 0 21 0 2 0 0 21 33 b - TP 97,8 Bus
0 13 1673 2 0 16 0 0 0 0 c - TP 98,2 Foot
0 12 0 3750 0 10 0 0 0 41 d - TP 98,3 Car
0 17 5 1 822 1 0 0 0 17 e - TP 95,2 Bike
0 5 0 31 21 2626 0 0 0 6 f - TP 97,7 Train
0 140 28 114 0 1 1026 0 0 0 g - TP 78,4 Tram
3 222 0 10 0 9 41 155 4 0 h - TP 34,9 Subway
16 0 0 0 0 0 0 0 1244 14 i - TP 97,6 Boat
18 42 15 5 8 21 0 7 26 2684 j - TP 95,0 Plane
Table 10, Confusion matrix for the best results
43
the exceptions of Train, Tram and Subway, all of which are being more often mistakenly
classified as Bus or Car.
Table 12 presents the training and prediction times required by the various classifiers when run
on a laptop (featuring an Intel Core i7-4700MQ CPU @ 2.40 GHz) to give an idea of the
requirements of each classifier. While training the classifiers on the target development Android
device (a Sony Xperia Z3 Compact), the corresponding training times were multiplied by a
factor of more than 5, making the Random Forest classifier eventually unsuitable for iterated
testing (training the classifier would take minutes instead of seconds). The table more
specifically shows the total time required to train the classifier and predict all values when
performing the 10-fold cross-validation with and without using the history set (HSS 0 and 50).
All time values presented are in milliseconds. As can be seen, the use of the history set adds a
seemingly indistinguishable amount of extra computation time (in the order of 1-2 ms for 30k
predictions at most).
Training
Prediction
Classifier HSS 0 HSS 10 HSS 20 HSS 30 HSS 50
Random
Forest
12053 ms 202 ms 183 ms 219 ms 201 ms 200 ms
Random Tree 188 ms 2 ms 2 ms 3 ms 3 ms 4 ms
Bayesian
Network
117 ms 13 ms 13 ms 15 ms 15 ms 16 ms
Naïve
Bayesian
24 ms 105 ms 105 ms 106 ms 108 ms 106 ms
Table 12, Time consumption of the tested classifiers.
Predicted values in each column, True values in each row.
a b c d e f g h i j
2561 16 0 1 0 22 0 0 0 0 a - TP 98,5 Idle
0 3372 0 92 0 0 0 0 41 69 b - TP 94,3 Bus
0 19 1666 10 0 9 0 0 0 0 c - TP 97,8 Foot
0 111 0 3636 0 0 0 0 0 66 d - TP 95,4 Car
0 26 11 7 795 4 0 0 0 20 e - TP 92,1 Bike
0 406 7 443 26 1766 0 0 0 41 f - TP 65,7 Train
0 229 44 345 0 10 680 0 0 1 g - TP 51,9 Tram
0 291 0 82 20 0 23 0 28 0 h - TP 0,0 Subway
26 0 0 0 0 0 0 0 1218 30 i - TP 95,6 Boat
41 76 29 3 11 25 0 0 37 2604 j - TP 92,1 Plane
Table 11, Confusion matrix for normalized acceleration values
44
5.5 Online Transportation Mode Detection
In addition to the offline analysis presented
above, online tests using the Random Tree
classifier was employed within the prototype
game. For all tests, the history set was used
(usually size 12) and sleep-settings were set to
the same number as the history set. Using a
setting of 12 meant that the background sensor
service should have been active for 1 minute,
then sleeping 1 minute, then restarting.
A screen within the game enabled users to view
the detected transports for the past day, as well
as other time-frames (minutes, hours, weeks).
Figure 16 shows how the screen was designed
within the app. On top the current sensor state
and detected transport could be seen, below that
some settings could be selected, a graph for the
chosen time is presented, and in the bottom a
list of the N last detected transports are listed.
In initial versions of the app (i.e. in progress
development phase), the history set size and
sleep sessions were configurable for testing purposes. In all tests with the 4 test-users the values
of the history set and sleep sessions was locked to 12.
Figure 16 also shows the detection results when being idle followed by a brief walk. The user
did not take a bus nor boat during that day, and as such those values are false positives. Figure
17 shows the results for when a user was in a bus and got off at a bus stop to change busses. As
can be seen, false positives arise again for Train and Car, as well as Plane. Similarly, Figure
18 shows the results of 1 hour of usage when walking, taking a bus and going by train, and the
respective false positives.
Figure 16, screenshot of the Transportation usage screen within Evergreen (1 day)
45
For both data gathering, and evaluation, some devices had difficulties or were not able to gather
Gyroscope data. For one of the test-users, his device would not let the Transport Detection
background service operate normally in the background, resulting always in near-0 total
seconds for the past 24 hours, as compared to thousands of seconds for other users.
Appendix 11 contains transcripts of all test-user interviews, some of which relates to the online
tests of the transport detection mentioned here.
Figure 17, Transportation Detection while in a Bus and getting of at a Bus stop (10 minutes total)
Figure 18, Transportation Detection for Walking, Bus and Train (1 hour)
46
6 DISCUSSION
Persuasion as a tool to change people’s behaviour has already been studied by many and
persuasive games as a useful tool is still being explored. One key disadvantage is that the effects
are possibly only short-term. Not so many persuasive games make use or focus on multiplayer
interactions, however, and by analysing the responses from our questionnaires it seems that
social factors such as competition would encourage more users to be persuaded to change their
lifestyles.
The testers of the game, Assaults of the Evergreen, were few but gave some invaluable insight
into the possible effects of deploying such a game on a larger scale. Further testing of this game
and similar games is suggested to verify if the potential behaviour changes would indeed come
to realization or if they are merely expectations.
To revisit the initial research questions:
• How well can we induce greener transportation choices by persuasive games?
Travel time may be reduced by between 0 and 25% for participants, depending primarily
on the participant’s current living situation.
• What aspects of persuasive games are impactful on transportation choices?
Using a game design based on iterative playing, highlighting co-operative and
competitive interactions, and highlighting the impact of real-life vehicle usage within
the game.
• How can one easily identify specific forms of transport (car, bus, bike, walk, train,
plane) without manual input and without significantly reducing battery life?
Using Machine learning algorithms together with a history set to remove noise provide
a good base for further testing. Random Forest may not be suited for games due to its
relative small performance gain and drastically increased computation time compared
to Random Tree, at least when a history set is used to reduce noise over time.
The transport algorithm that was presented was mostly an evolved version of one proposed by
Bedogni et al [32]. The addition of the normalization of accelerometer values was not found in
contemporary literature and could deserve some further analysis. User experience-based
analysis may be required in order to fully make the approach device- and orientation-
independent, as some orientations were prone to larger errors in gravity measurements than
47
others (left- and right-side), and there may be biases in the sampled data towards some
orientations which may produce errors in specific use-cases.
Compared with the results of Bedogni et al [32], our results were generally inferior. This is
probably in part due to the lesser quantity of sampled data. The data accumulated and
generously shared with us by Bedogni et al totalled 38’061 samples, each representing 10
seconds. This represents a total figure of 105.7 hours, as compared to our total of 29.3 hours.
Running the same high-performance classifiers (RF, RT) on their data (7 classes of Idle, Bus,
Foot, Car, Bike, Train, Tram) produced in general better results: 87% TP rate for RF, 82% TP
rate for RT (see Appendix 6 and 7 for details, compare with Appendix 4 and 5).
For some of our classes data was just insufficiently sampled. For example, Subway only has
444 samples, and since its data shares many characteristics with other transports, the TP rate is
logically low. The trend of “the more, the better” was observed when gathering samples for all
transports. Classification tests were run regularly as each batch of data was collected, and for
those transports where classification was low initially accuracy improved after more samples
were gathered.
Persuasion as a tool to change people’s behaviour has already been noted as being a useful tool
but has its disadvantages and limitations (possibly short-term effects). Not so many existing
serious games have provided facilities for multiplayer interactions. However, an analysis of the
responses from our questionnaires seems to reveal that social factors such as competition would
encourage more users to be persuaded to change their lifestyles.
Due to the study being short-term, and few respondents played the game in multiplayer mode
for the measured 10-day period, only an assumption could be made on the possible long-term
effects and impacts a game such as Evergreen could have. Assuming Evergreen or a similar
game gets popular and more than 5% of the Swedish population start playing it, and assuming
an average behavioural change of 10% would be realized, then an estimated one hundred
thousand tonnes of carbon dioxide equivalents could be saved each year. This is shown in
equation 3, and is based on the Swedish transports emissions for the year of 2014, where Swedes
emitted a total of 19.95 MtCO2 from transportation alone [8]. Seeing as the Swedish population
has begun emitting more emissions internationally, however, such a game would have to
properly identify and integrate transportation by plane – which we have seen in this work might
48
be feasible. This figure also does not account for the increased battery usage from playing the
game.
19.9522255 𝑀𝑡𝐶𝑂2e × 0.05 × 0.10 = 99.7611275 𝑘𝑡𝐶𝑂2𝑒 (3)
What is worth noting is that even for those people who would not play Evergreen or a similar
game for a long time, it could still have effects on the long-term.
As a final note, 2 of the 4 players were still playing the game 50 days after it was initially
published. As such, the game’s design may be considered a success as far as playing experience
is concerned, despite all limitations and possible improvements mentioned earlier.
49
7 CONCLUSIONS AND FUTURE WORK
We have presented a prototype persuasive game with multiplayer interactions, called Assaults
of the Evergreen, embedded with a transportation detection algorithm to enable a feedback from
real-life actions into the game. An existing approach to transportation mode recognition based
on Accelerometer and Gyroscope data was analysed and developed further to ensure that it is
fully device- and orientation-independent.
Results from the transport classifier tests show that even with normalized acceleration
measurements, the proposed transportation mode detection can reach a classification true-
positive rate of up to 87% for 10 classes. The corresponding value for non-normalized
acceleration measurements reached a classification true-positive rate of up to 95%. Quantitative
and qualitative data was gathered by the help of questionnaires and interviews to measure the
expectations and possible effects of deploying a persuasive game such as Evergreen.
Results from the game-testers show that deploying persuasive games to promote greener
transportation may have some effect, but that it will vary depending on each individual’s
situation. Testers playing the game for at least 10 days stated that they were trying to choose
greener forms of transportation between and 0 and 25% or their total travel time, and
highlighted some improvements that could make a game such as Evergreen successful.
Future work could include larger test groups over longer periods of times to evaluate
persuasiveness of games such as Evergreen and actual change, sampling more data to improve
transportation classifier stability, testing the transport classifier with more users to ensure its
stability (user-experience tests), and test persuasiveness with other types of behavioural
changes.
Other behavioural changes to reduce our environmental footprint could also be worth
investigating using persuasive games. One such example is what we choose to eat. Reports
suggest that up to 10% of our total consumption footprint, or half of our footprint concerning
what we eat, could be reduced by switching to a vegetarian diet [48]. However, using persuasive
games with most behavioural changes requires user input for step-by-step analysis of any
change, and would thus have different results and evaluation methods compared to the
prototype game and behavioural change investigated in this report.
50
REFERENCES
[1] IPCC, “Climate Change 2014: Synthesis Report,” IPCC, Geneva, 2014.
[2] A. Klimova, E. Rondeau, K. Andersson, J. Porras, A. Rybin and A. Zaslavsky, “An international
Master's program in green ICT as a contribution to sustainable development,” Journal of Cleaner
Production, vol. 135, pp. 223-239, 2016.
[3] J. Porras, A. Seffah, E. Rondeau, K. Andersson and A. Klimova, “PERCCOM: A Master Program in
Pervasive Computing and COMmunications for sustainable development,” in Software Engineering
Education and Training (CSEET), 2016 IEEE 29th International Conference on, 2016.
[4] I. H. Witten, E. Frank, M. A. Hall and C. J. Pal, Data Mining: Practical machine learning tools and
techniques, Morgan Kaufmann, 2016.
[5] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann and I. H. Witten, “The WEKA data mining
software: an update,” ACM SIGKDD explorations newsletter, vol. 11, no. 1, pp. 10-18, 2009.
[6] S. Bin and H. Dowlatabadi, “Consumer lifestyle approach to US energy use and the related CO2
emissions,” Energy policy, pp. 197-208, 2005.
[7] Naturvårdsverket, “Konsumptionsbaserade utsläpp av växthusgaser, i Sverige och i andra länder,”
Naturvårdsverket (Swedish Environmental Protection Agency), 12 December 2016. [Online]. Available:
http://www.naturvardsverket.se/Sa-mar-miljon/Statistik-A-O/Vaxthusgaser-konsumtionsbaserade-
utslapp-Sverige-och-andra-lander/. [Accessed 9 March 2017].
[8] Naturvårdsverket, “Konsumtionsbaserade utsläpp av växthusgaser, hushållens transporter och
konsumtion av livsmedel,” Naturvårdsverket (Swedish Environmental Protection Agency), 12 December
2016. [Online]. Available: http://www.naturvardsverket.se/Sa-mar-miljon/Statistik-A-O/Vaxthusgaser-
konsumtionsbaserade-utslapp-hushall-livsmedel-och-transport-/. [Accessed 9 March 2017].
[9] “Antal flygresor per invånare,” Naturvårdsverket (Swedish Environmental Protection Agency), 2016.
[Online]. Available: http://www.naturvardsverket.se/Sa-mar-miljon/Statistik-A-O/Klimat-antal-
flygresor-per-invanare/. [Accessed 9 March 2017].
[10] J. K. Swim, S. Clayton and G. S. Howard, “Human behavioral contributions to climate change:
psychological and contextual drivers.,” American Psychologist, vol. 66, no. 4, pp. 251-264.
[11] “World population projected to reach 9.7 billion by 2050,” United Nations Department of Economic and
Social Affairs, 29 July 2015. [Online]. Available:
http://www.un.org/en/development/desa/news/population/2015-report.html. [Accessed 14 May 2017].
[12] S. Pauliuk and D. B. Müller, “The role of in-use stocks in the social metabolism and in climate change
mitigation,” Global Environmental Change, vol. 24, pp. 132-142, 2014.
[13] EEA, “The European environment - state and outlook 2015: synthesis report,” European Environment
Agency, Copenhagen, 2015.
[14] rjmarsan, “Weka-for-Android, the Weka project with the GUI components removed so it works with
Android,” 16 February 2011. [Online]. Available: https://github.com/rjmarsan/Weka-for-Android/.
[Accessed 6 March 2017].
[15] T. M. Connolly, E. A. Boyle, E. MacArthur, T. Hainey and J. M. Boyle, “A systematic literature review
of empirical evidence on computer games and serious games,” Computers & Education, vol. 59, no. 2,
pp. 661-686, 2012.
[16] R. Khaled, P. Barr, J. Noble, R. Fischer and R. Biddle, “Persuasive Technology: Second International
Conference on Persuasive Technology, PERSUASIVE 2007, Palo Alto, CA, USA, April 26-27, 2007,
Revised Selected Papers,” in Fine Tuning the Persuasion in Persuasive Games, Berlin, Heidelberg,
Springer, 2007, pp. 36-47.
[17] T. Lavender, “Games Just Wanna Have Fun…Or Do They?,” in Proceedings of Canadian Games Study
Association Symposium, 2006.
[18] J. Froehlich, T. Dillahunt, P. Klasnja, J. Mankoff, S. Consolvo, B. Harrison and J. A. Landay,
“UbiGreen: investigating a mobile tool for tracking and supporting green transportation habits,” in
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2009.
[19] R. Orji, R. L. Mandryk, J. Vassileva and K. M. Gerling, “Tailoring persuasive health games to gamer
type,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, 2013.
51
[20] S. Deterding, “Coding conduct, Persuasive Design for digital media,” 21 February 2017. [Online].
Available: http://codingconduct.cc/.
[21] J. Ferrara, “Games for Persuasion,” Games and Culture, vol. 8, no. 4, pp. 289-304, 2013.
[22] S. Reddy, M. Mun, J. Burke, D. Estrin, M. Hansen and M. Srivastava, “Using mobile phones to
determine transportation modes,” ACM Transactions on Sensor Networks (TOSN), p. 13, 2010.
[23] B. Nham, K. Siangliulue and S. Yeung, “Predicting mode of transport from iphone accelerometer data,”
Standford University Class Project, 2008.
[24] P. Ernest, R. Mazl and L. Preucil, “Train locator using inertial sensors and odometer,” in Intelligent
Vehicles Symposium, 2004.
[25] D. Anguita, A. Ghio, L. Oneto, X. Parra and J. L. Reyes-Ortiz, “Human Activity Recognition on
Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine,” in Ambient Assisted
Living and Home Care: 4th International Workshop, Vitoria-Gasteiz, 2012.
[26] J.-L. Reyes-Ortiz, L. Oneto, A. Sama, X. Parra and D. Anguita, “Transition-aware human activity
recognition using smartphones,” Neurocomputing, vol. 171, pp. 754-767, 2016.
[27] T. Nick, E. Coersmeier, J. Geldmacher and J. Goetze, “Classifying means of transportation using mobile
sensor data,” in Neural Networks (IJCNN), The 2010 International Joint Conference on, 2010.
[28] S. Hemminki, P. Nurmi and S. Tarkoma, “Accelerometer-based transportation mode detection on
smartphones,” in Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems,
New York, 2013.
[29] O. Lorintiu and A. Vassilev, “Transportation mode recognition based on smartphone embedded sensors
for carbon footprint estimation,” in Intelligent Transportation Systems (ITSC), 2016 IEEE 19th
International Conference on, 2016.
[30] A. Jahangiri and H. A. Rakha, “Applying machine learning techniques to transportation mode
recognition using mobile phone sensor data,” IEEE transactions on intelligent transportation systems, p.
IEEE, 2015.
[31] L. Bedogni, M. Di Felice and L. Bononi, “By train or by car? Detecting the user's motion type through
smartphone sensors data,” in Wireless Days (WD), Dublin, 2012.
[32] L. Bedogni, M. Di Felice and L. Bononi, “Context-aware Android applications through transportation
mode detection techniques,” Wireless Communications and Mobile Computing, pp. 2523-2541, 2016.
[33] L. Breiman, “Bagging Predictors,” University of California, Department of Statistics, Berkeley, 1994.
[34] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5-32, 2001.
[35] I. Ben-Gal, “Bayesian Networks,” in Encyclopedia of statistics in quality and reliability, Wiley Online
Library, 2007.
[36] A. W. Moore and M. S. Lee, “Cached Sufficient Statistics for Efficient Machine Learning with Large
Datasets,” Journal of Artificial Intelligence Research, vol. 8, no. 3, pp. 67-91, 1998.
[37] G. F. Cooper and E. Herskovits, “A Bayesian method for constructing Bayesian belief networks from
databases,” in Proceedings of the conference on Uncertainty in AI, 1990.
[38] G. Cooper and E. Herskovits, “A Bayesian method for the induction of probabilistic networks from
data,” Machine Learning, vol. 9, no. 4, pp. 309-347, 1992.
[39] G. John and P. Langley, “Estimating Continuous Distributions in Bayesian Classifiers,” in Eleventh
Conference on Uncertainty in Artificial Intelligence, 1995.
[40] T. W. Malone, “What makes things fun to learn? Heuristics for designing instructional computer
games,” in Proceedings of the 3rd ACM SIGSMALL symposium and the first SIGPC symposium on
Small systems, 1980.
[41] E. Adams, “Chapter 4, Understanding Your Player,” in Fundamentals of Game Design, third edition,
Pearson Education, Inc., 2014, pp. 81-102.
[42] J. VandenBerghe, “The 5 Domains of Play: Applying Psychology's Big 5 Motivation Domains to
Games, talk at GDC 2012,” Ubisoft, 2012. [Online]. Available:
http://www.gdcvault.com/play/1015595/The-5-Domains-of-Play. [Accessed 16 May 2017].
[43] L. R. Goldberg, “The structure of phenotypic personality traits.,” American psychologist, vol. 48, no. 1,
p. 26, 1993.
[44] R. Bartle, “Hearts, clubs, diamonds, spades: Players who suit MUDs,” Journal of MUD research, vol. 1,
no. 1, p. 19, 1996.
52
[45] M. Serino, K. Cordrey, L. McLaughlin and R. L. Milanaik, “Pokémon Go and augmented virtual reality
games: a cautionary commentary for parents and pediatricians,” Current opinion in pediatrics, vol. 28,
no. 5, pp. 673-677, 2016.
[46] S. Michie, M. M. van Stralen and R. West, “The behaviour change wheel: a new method for
characterising and designing behaviour change interventions,” Implementation Science, vol. 6, no. 1, p.
42, 2011.
[47] E. Hedemalm, “Evergreen - the Game, Prototype table-top RPG/Strategy rules,” 2 November 2016.
[Online]. Available:
https://docs.google.com/document/d/155rwYDJeFLjx18rsv1tPCDg5rYvEK2pewqZfo4WNhxs/edit?usp
=sharing.
[48] Naturvårdsverket, “Köttkonsumtionens klimatpåverkan, Drivkrafter och styrmedel,” Naturvårdsverket
(Swedish Environmental Protection Agency), Stockholm, 2013.
APPENDIX 1. Evergreen - Paper prototype
(Continues)
APPENDIX 1. (continues) Evergreen - Paper prototype
(Continues)
APPENDIX 1. (continues) Evergreen - Paper prototype
APPENDIX 2. Evergreen – Visual mockup
APPENDIX 3. Evergreen – Android prototype screenshots
APPENDIX 4. Classification results on sampled data – RF === Run information ===
Scheme: weka.classifiers.trees.RandomForest -P 100 -I 100 -num-slots 1 -K 0 -M 1.0 -V 0.001 -S 1
Relation: sensor-weka.filters.unsupervised.attribute.Remove-R1
Instances: 21096
Attributes: 9
accMin
accMax
accAvg
accStdev
gyroMin
gyroMax
gyroAvg
gyroStdev
transport
Test mode: 10-fold cross-validation
=== Classifier model (full training set) ===
RandomForest
Bagging with 100 iterations and base learner
weka.classifiers.trees.RandomTree -K 0 -M 1.0 -V 0.001 -S 1 -do-not-check-capabilities
Time taken to build model: 11.95 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 13985 66.2922 %
Incorrectly Classified Instances 7111 33.7078 %
Kappa statistic 0.6136
Mean absolute error 0.0918
Root mean squared error 0.2122
Relative absolute error 52.547 %
Root relative squared error 71.7917 %
Total Number of Instances 21096
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0,686 0,024 0,799 0,686 0,738 0,707 0,944 0,827 Idle
0,650 0,085 0,590 0,650 0,618 0,544 0,899 0,688 Bus
0,759 0,023 0,745 0,759 0,752 0,730 0,967 0,837 Foot
0,681 0,082 0,647 0,681 0,664 0,587 0,916 0,761 Car
0,684 0,012 0,707 0,684 0,695 0,683 0,970 0,763 Bike
0,604 0,061 0,593 0,604 0,598 0,539 0,915 0,633 Train
0,508 0,032 0,516 0,508 0,512 0,480 0,925 0,587 Tram
0,288 0,006 0,520 0,288 0,371 0,378 0,904 0,365 Subway
0,759 0,026 0,648 0,759 0,699 0,681 0,975 0,746 Boat
0,707 0,037 0,765 0,707 0,735 0,692 0,938 0,813 Plane
Weighted Avg. 0,663 0,050 0,667 0,663 0,663 0,614 0,930 0,735
=== Confusion Matrix ===
a b c d e f g h i j <-- classified as
1783 150 103 125 33 52 69 31 158 96 | a = Idle
78 2163 64 374 38 251 139 19 67 134 | b = Bus
61 89 1294 56 64 19 42 8 37 34 | c = Foot
67 370 53 2598 66 330 137 9 51 132 | d = Car
23 28 108 66 590 6 31 0 2 9 | e = Bike
23 293 26 287 4 1624 94 36 82 220 | f = Train
27 161 30 235 15 107 665 1 56 12 | g = Tram
36 117 16 36 3 43 25 128 26 14 | h = Subway
55 74 14 36 1 54 52 4 967 17 | i = Boat
79 224 30 204 20 252 35 10 46 2173 | j = Plane
APPENDIX 5. Classification results on sampled data – RT
=== Run information ===
Scheme: weka.classifiers.trees.RandomTree -K 0 -M 1.0 -V 0.001 -S 1
Relation: sensor-weka.filters.unsupervised.attribute.Remove-R1
Instances: 21096
Attributes: 9
accMin
accMax
accAvg
accStdev
gyroMin
gyroMax
gyroAvg
gyroStdev
transport
Test mode: 10-fold cross-validation
=== Classifier model (full training set) ===
RandomTree
==========
<Tree details omitted to conserve space>
Size of the tree : 13141
Time taken to build model: 0.22 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 11683 55.3802 %
Incorrectly Classified Instances 9413 44.6198 %
Kappa statistic 0.4896
Mean absolute error 0.0893
Root mean squared error 0.2986
Relative absolute error 51.1167 %
Root relative squared error 101.0269 %
Total Number of Instances 21096
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0,658 0,048 0,656 0,658 0,657 0,609 0,805 0,474 Idle
0,494 0,093 0,499 0,494 0,496 0,402 0,700 0,326 Bus
0,655 0,030 0,658 0,655 0,656 0,626 0,814 0,461 Foot
0,564 0,098 0,560 0,564 0,562 0,465 0,734 0,396 Car
0,565 0,018 0,569 0,565 0,567 0,549 0,774 0,341 Bike
0,459 0,074 0,477 0,459 0,468 0,392 0,693 0,288 Train
0,439 0,046 0,389 0,439 0,413 0,372 0,697 0,206 Tram
0,255 0,018 0,238 0,255 0,246 0,229 0,618 0,076 Subway
0,560 0,026 0,580 0,560 0,570 0,543 0,767 0,352 Boat
0,631 0,061 0,640 0,631 0,635 0,574 0,785 0,457 Plane
Weighted Avg. 0,554 0,064 0,555 0,554 0,554 0,490 0,745 0,372
=== Confusion Matrix ===
a b c d e f g h i j <-- classified as
1711 140 110 123 46 81 69 56 133 131 | a = Idle
146 1643 106 456 46 340 195 86 84 225 | b = Bus
122 92 1116 69 116 27 39 41 29 53 | c = Foot
140 415 73 2150 97 346 268 38 61 225 | d = Car
38 57 119 86 488 16 35 7 1 16 | e = Bike
76 345 32 402 9 1234 148 57 79 307 | f = Train
45 143 46 235 17 111 575 25 58 54 | g = Tram
54 83 25 32 8 54 23 113 24 28 | h = Subway
132 99 30 62 7 74 73 30 714 53 | i = Boat
143 278 39 223 23 306 52 22 48 1939 | j = Plane
APPENDIX 6. Classification results on data provided by L. Bedogni – RF
=== Run information ===
Scheme: weka.classifiers.trees.RandomForest -P 100 -I 100 -num-slots 1 -K 0 -M 1.0 -V 0.001 -S 1
Relation: sensorBedogni-weka.filters.unsupervised.attribute.Remove-R1
Instances: 38061
Attributes: 8
accMax
accAvg
accStdev
gyroMin
gyroMax
gyroAvg
gyroStdev
transport
Test mode: 10-fold cross-validation
=== Classifier model (full training set) ===
RandomForest
Bagging with 100 iterations and base learner
weka.classifiers.trees.RandomTree -K 0 -M 1.0 -V 0.001 -S 1 -do-not-check-capabilities
Time taken to build model: 15.07 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 33135 87.0576 %
Incorrectly Classified Instances 4926 12.9424 %
Kappa statistic 0.8188
Mean absolute error 0.0542
Root mean squared error 0.1643
Relative absolute error 26.3967 %
Root relative squared error 51.2826 %
Total Number of Instances 38061
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0,878 0,003 0,913 0,878 0,895 0,891 0,993 0,954 Idle
0,689 0,007 0,782 0,689 0,733 0,726 0,977 0,809 Bus
0,566 0,008 0,747 0,566 0,644 0,638 0,972 0,721 Foot
0,910 0,049 0,859 0,910 0,884 0,845 0,981 0,937 Car
0,704 0,014 0,731 0,704 0,718 0,703 0,976 0,768 Bike
0,898 0,087 0,888 0,898 0,893 0,811 0,971 0,963 Train
0,903 0,016 0,916 0,903 0,910 0,893 0,993 0,972 Tram
Weighted Avg. 0,871 0,054 0,869 0,871 0,869 0,819 0,978 0,933
=== Confusion Matrix ===
a b c d e f g <-- classified as
1127 0 0 107 0 49 1 | a = Idle
0 899 2 26 89 151 137 | b = Bus
0 2 893 16 27 623 16 | c = Foot
62 15 5 8546 25 727 16 | d = Car
1 84 38 21 1349 176 246 | e = Bike
45 37 250 1209 51 14834 85 | f = Train
0 112 7 24 304 140 5487 | g = Tram
APPENDIX 7. Classification results on data provided by L. Bedogni – RT
=== Run information ===
Scheme: weka.classifiers.trees.RandomTree -K 0 -M 1.0 -V 0.001 -S 1
Relation: sensorBedogni-weka.filters.unsupervised.attribute.Remove-R1
Instances: 38061
Attributes: 8
accMax
accAvg
accStdev
gyroMin
gyroMax
gyroAvg
gyroStdev
transport
Test mode: 10-fold cross-validation
=== Classifier model (full training set) ===
RandomTree
==========
<Tree details omitted to conserve space>
Size of the tree : 10117
Time taken to build model: 0.28 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 31042 81.5586 %
Incorrectly Classified Instances 7019 18.4414 %
Kappa statistic 0.7436
Mean absolute error 0.0527
Root mean squared error 0.2295
Relative absolute error 25.6533 %
Root relative squared error 71.6301 %
Total Number of Instances 38061
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0,867 0,005 0,848 0,867 0,857 0,852 0,931 0,739 Idle
0,639 0,013 0,632 0,639 0,636 0,623 0,813 0,416 Bus
0,537 0,021 0,526 0,537 0,532 0,511 0,758 0,302 Foot
0,830 0,056 0,830 0,830 0,830 0,774 0,887 0,731 Car
0,608 0,022 0,598 0,608 0,603 0,582 0,793 0,383 Bike
0,849 0,115 0,850 0,849 0,849 0,734 0,867 0,787 Train
0,868 0,023 0,880 0,868 0,874 0,850 0,923 0,785 Tram
Weighted Avg. 0,816 0,070 0,816 0,816 0,816 0,746 0,873 0,718
=== Confusion Matrix ===
a b c d e f g <-- classified as
1113 1 1 97 1 68 3 | a = Idle
1 833 9 42 128 126 165 | b = Bus
2 7 847 26 62 605 28 | c = Foot
126 40 27 7796 33 1345 29 | d = Car
2 122 57 37 1164 169 364 | e = Bike
68 125 647 1361 165 14014 131 | f = Train
1 189 21 34 393 161 5275 | g = Tram
APPENDIX 8. Expectations Questionnaire
Persuasive games & Transportation: Expectations
An initial analysis of perceptions around games, persuasive/serious games in general and their relation to choice of
transportation. The survey is anonymous and serves as a basis for a Master thesis work in Pervasive computing and
communications for Sustainable Development.
Q1. How often do you play games?
Answers between 1 and 5. 1 labelled “Rarely if ever”, 5 labelled “Several hours a day”
Q2. When you do play games, on which platform or which mediums do you play games most of the time?
Check all checkboxes that apply.
• Smartphones (iOS, Android, Blackberry, Windows phone, etc.)
• Consoles (PlayStation 3/4, XBox 360/One, Wii U, etc.)
• Hand-held Consoles (PlayStation Portable/Vita, Nintendo 3DS, etc.)
• PC (any OS, any distribution form: Steam, Origin, digital download, bought discs etc.)
• Traditional games (board-games, pen & paper RPGs, card-games, etc.)
(Continues)
(Continues)
APPENDIX 8. (Continues) Expectations Questionnaire
Q3. Have you heard about Serious Games before answering this survey? *
Answers between 1 and 5. 1 labelled ”Never heard of it!”, 5 labelled ”I’m an expert!”
Serious Games
Serious games are games designed for another purpose than pure entertainment. They can made from an educational,
promotional or other kind of viewpoint. Examples include Edutainment games supposed to educate you in a fun way, and
Exergames which promote physical fitness. Simulators are also related as they are usually used for purely educational purposes,
often lacking the "fun" present in other games.
Q4. To which extent do you think a game could impact your lifestyle?
Answers between 1 and 5. 1 labelled ”Not at all”, 5 labelled ”A lot”
Q5. If there was a game designed to improve your daily choice of transportation, would you consider playing it?
Answers between 1 and 5. 1 labelled ”No, never!”, 5 labelled ”Sure, why not”
APPENDIX 8. (Continues) Expectations Questionnaire
Q6. Depending on your answer to the previous question: If you would consider playing
it, how do you image the game could look like? How would it work? How would you design
it? If you would rather abstain, how come?
Long text answer.
Answers listed below. Irrelevant or too short ones omitted. 4 answers were omitted as
basically saying ”Don’t know”
• I love puzzles, so, I would enjoy picking up the best suitable choice of transportation for a certain destination, having
in mind the importance of time, distance, number of passengers...
• I think the game would endeavor to convince me that my current choice of transportation is bad through the
presentation of real-life data and statistics.
• The game would have to be natural and adjust to my schedules. I imagine a game that helps me wake up and finding
the best route somewhere
• Entertaining, informative and thought provoking.
• No idea, I would just play any game if it was fun
• Depends how it's linked to my other apps. People have too many apps anyway so having one more is out of the
question. Maybe working like health monitors that could gather your transportation choices and show
weekly/monthly summary.
• A lot of "how " questions :P
• Maybe a mobile app with leaderboards, competitions, rewards, etc (/re gamification)
• I don't like games much so I've no idea about this.
• Maps showing paths and images of transport to use, with some exciting challenges.
• I imagine it could enlighten the impact of our transport, on the global warming and our daily lives (pollution etc).
Show us that a difference actually can be made as an individual, without any extreme efforts. The game would need
to be stimulating and giving feedback, in order for people to continue and progress. Spontaneous thought, a city-
building game such as SimCity, with parameters included such as CO2 emissions that is calculated and presented,
depending on what choices the player has made regarding buildings, public transport etc. The city could thereafter
maybe be "scored" on a scoreboard where it is compared to other theoretical/online-players cities, so there's a factor
of competition in it (fun & motivating?).
• I would probably have to design it very well, it would be very hard to incentivize or influence people into changing
mode of transportation with a game.
• Some sort of simulation or more of a puzzel type of game. Where you need to get and remember important parts.
• Maybe resource management, try and design so the player realizes the advantages of other transportation. Would be
hard though needs to be on a global scale to show the seriousness but still local enough to make the player feel like
he/she can make a difference.
• I use my bike to go everywhere. So I don't k how to improve my means of transportation without paying for the bus
or get a car.
• A game that involves physical activity
• Some kind of assignments and getting rewards in forms of superpowers or recognition.
• Android game
• the subject doesn't seem interesting
• I'm always using the same transportation, so I wouldn't play it to improve the daily choice.
• Like a city builder maybe
• Har ingen aning hur det skulle funka!
• Maybe it should ask me a daily question about where i am going, and how i intend to get there. Maybe causing a
subconscious feeling of guilt or something to get your into the mode of "not being a slacker".
• Pokemon go is on a good start here. But developing that further and involving peoples life choices and sharing it with
others is a short term solution. In the long run you not only have to reward good choices but also punish bad once.
• Like every other WWII-game! Drive a tank and BOOOOOM!
• Probably a game where u get to create your green vehicle. IDK..that is a very shallow idea i have
• Your game idea is pretty interesting. I guess just try to simplify it more for first deployment and you can develop
more if it is a success.
• I am not so influenced by games. But if I were to be influenced, I would want some kind of reinforcement, or in other
words the game should some how strongly show me that I am benifitting / benifitted in some way by making this
choice.
• Work in the background, and sends me notification of achievement or possible future achievements if certain things
are done .
• reward rather than punish user for its actions, not time consuming, need to still be interesting even after few
days/weeks, social aspect?
• I would say on smartphone but it has to have low battery consumption. It would be using my location and not send
it to a third party
(Continues)
APPENDIX 8. (Continues) Expectations Questionnaire
(Answers to Q6 continued)
• A neat game for your smartphone devices not necessarily demanding much performance, it should have a
summarisation of your emissions where you can easily track them.
• I could play if it doesn't take much time
• Maybee if the game contains sportcars
• It feels that it would be limited if you have to incorporate educational elements.
• I'm not very interested in playing to learn about my daily transportation. BUT, If I would try, though, maybe it would
make me choose between local bus, car or bike, to arrive to a location. Depending of which type transportation you
choose, the game will show various other alternatives to reach the location in ,an enviromentally, or just in a more
efficient way. Also, it could show pros and cons with every altrernative.
Q7. Do you think a game designed to change people's choice of transportation could be successful?
Answers between 1 and 5. 1 labelled ”No”, 5 labelled ”Sure”
Q8. Depending on your previous answer: Why? Why not?
Long text answer.
Answers listed below. Irrelevant or too short ones omitted. Some answers translated from Swedish.
• Yes, provided that the game is still pretty close to reality and as mentioned, enlightens how the player could make a
difference, and also what actions has been performed in-game that had positive effects on the virtual-environment.
• Because any game can be successful, if well designed and well-advertised enough.
• Maby for the newer generation, but not the older.
• Hard to change a persons routines, not impossible but very hard.
• People tend to be good at finding their optimal transportation routines.
• Because people are nowadays open minded and welcome new ideas
• It could influence people to make more "greener" choices etc. It's also a conversation starter for both social and
environmental diskussions.
• It depends in the person paying the game and how they affected by it
• If it is well promoted
• Depends on the medium, on the graphics and, most of all, on the advertising. Could be that everyone likes it, but it's
possible that no one would play it at all.
• If enough people play it and discuss their experiences with it.
• Might be
• Would probably depend on how satisfied they are with the current situation.
• Because we are a lazy breed and we are good at making excuses for choosing the more comfortable way of
transportation. But we are at the same time the opposite.
• Depends on where the person lives
• Its right in time at the moment
• Can be fun (Continues)
APPENDIX 8. (Continues) Expectations Questionnaire
(Answers to Q8 continued)
• If the game have really good game design and elements, why not?
• It may be used as awareness to shared transport like I appreciate the idea of blabla car.
• A person need to really want to change his habit
• People need more incentives than a game can provide
• People are usually set in their way, it takes quite a lot to change habits
• It's a way of introduction and also to give a wider way of options for improving a system.
• I think the underlying choice of transportation is separate from games. A game might be the final drop that make
some people ride a bike instead of driving a car, but there'll be just as many people who just won't play, if not more.
• On spring I launched an experiment among my workers. Just invited them to bike to work certain Friday. Many
people did it, because they felt it as a challenge. Then I find out at our university every department has a team of
people biking and collecting kms, there is a leader board of which department has biked the most kms In a
week/month/year. Funny thing, they do it because they like the competition although the website of leaderboard is
bad. Moreover the people doing it usually lives far or takes extra long routes home to collect more kms. Many people
do it and there are always more. I guess this are gamified activities that changed their lives.
• For some it could just be a form of entertainment but for others it may encourage them to actually think about
changing their lifestyle choice.
• Maby for a short while, but people would go back to thier ways.
• Depends how it's linked with the other apps the user is used. If well then possibly yes.
• It could be successful to some extent.
• it depends on how much people really understand the ultimate purpose of game instead of playing just for the sake
of entertainment
• I am not really sure about it. If you tell people you want them to play a serious game that will change their choice of
transportation, you might be able to convince a specific group of people who are motivated to do so, but I am not so
sure about the gen. Pop . Update: you should write the thesis content thing on top. So thst people will understand
what are you tryin to do. Multiplayer, focus on social interaction can totally skew this survey in positive side if people
read it before/ on the very top.
• Because Pokemon go made everyone walk everywhere that's why
• there is a frontier between game and reality, the action taken in games are not always the same that the ones taken in
real life (generally speaking, not serious game wise). translating some morale/ways of doing from the virtual world
to the real one might be a challenging task. Does using augmented reality lower the difficulty to cross virtual->real
world for morale?
• It would be awesome! I think the game would open people's minds on they're choice of transportation. The game
would give the people they're own way to go and follow in the most desirable fashion.
• depends on the art and the mechanics. how a game pierces a persons mind
• It is hard to convince people to change their way of living
• Again hard to say
• It would get some mileage from being a "better option"-game but contentwise I think it would fall short.
• It would be great to present it to students who are about to take their drivers license. Everyone could have use of that
kind of information, really.
• I guess people would be more influenced if they were more aware of how their emission costs looked like.
• I guess to younger people with more free time it could. I would target schools for distribution
(Continues)
APPENDIX 8. (Continues) Expectations Questionnaire
Thesis content: Multiplayer Strategy/RPG game
I will be working with developing a Smartphone-based Multiplayer Strategy/Role-playing game to try and promote greener
modes of transportation. The game will have a heavy focus on regular gameplay and social interactions, but will also have
elements of gameplay that are directly related to real-life actions. Development has already begun on an Android prototype.
Q9. Would you be interested in following the development of the game?
Check all checkboxes that apply.
• Yes, I would like to test the final game (March/April)
• Yes, I would like to be a beta-tester (starting December/January)
• Yes, I am interested in the design of the game. Do you have a blog?
• No, not really
• Other:
APPENDIX 9. Pre-testing Questionnaire
Evergreen testers: Background & Expectations
Please enter information so that a comparison can be conducted at the end of the study. The play-testing trials are set to be a
duration between a few days up to a couple of weeks or longer. Playtesting in conjunction to this Master thesis research may
end at any point in time, but may also continue for a longer period of time if there is interest from players.
Testers are free to leave the study at any point in time, but are encouraged to fill out the evaluation form whenever they
intend to cancel their playtesting. Testers are also encouraged to invite other testers, since the game is multiplayer in nature.
The game has been developed during a limited period of time, so bear that in mind!
The e-mail addresses are collected for statistical correlation purposes, and will be used to correlate your answers now with
answers provided in the evaluation questionnaire. All data will be anonymized before presentation.
Q1. Email address *
Text answer. 24 unique respondents.
Q2. You are a *
Mark only one.
• Man
• Woman
• Other
Q3. Aged *
Mark only one.
• 18 or younger
• 19 - 25
• 26 - 35
• 36 - 45
• 46 - 55
• 56 - 65
• 66 or older
Q4. Your current occupation *
Mark only one.
• Student
• Working (full-time)
• Working (part-time)
• Unemployed
• Retired
(Continues)
APPENDIX 9. (Continues) Pre-testing Questionnaire Q5. When going somewhere on a daily basis (to work, place of studies, back home), what transports do you usually use? *
Check all checkboxes that apply.
• Walking / Running
• Bike
• Car
• Bus
• Train
• Tram
• Other:
Q6. How often do you play games? (any platform or medium) *
Mark only one.
• Daily
• A few times a week
• A few times a month
• A few times a year
• Never
(Continues)
APPENDIX 9. (Continues) Pre-testing Questionnaire
Q7. When you do play games, on which platform or which mediums do you play games most of the time? *
Check all checkboxes that apply.
• Smartphones (iOS, Android, Blackberry, Windows phone, etc.)
• Consoles (PlayStation 3/4, XBox 360/One, Wii U, etc.)
• Hand-held Consoles (PlayStation Portable/Vita, Nintendo 3DS, etc.)
• PC (any OS, any distribution form: Steam, Origin, digital download, bought discs etc.)
• Traditional games (board-games, pen & paper RPGs, card-games, etc.)
Q8. Have you heard about Serious Games before answering this survey? *
Answers between 1 and 5. 1 labelled ”Never heard of it”, 5 labelled ”I’m an expert!”
Serious Games
Serious games are games designed for another purpose than pure entertainment. They can made from an educational,
promotional or other kind of viewpoint. Examples include Edutainment games supposed to educate you in a fun way, and
Exergames which promote physical fitness. Simulators are also related as they are usually used for purely educational purposes,
often lacking the "fun" present in other games.
(Continues)
APPENDIX 9. (Continues) Pre-testing Questionnaire
Q9. To which extent do you think a game could impact your lifestyle? *
Answers between 1 and 5. 1 labelled ”Not at all”, 5 labelled ”A lot”
Q10. What about others, do you think a game designed to change people's choice of transportation could be successful in
general? *
Answers between 1 and 5. 1 labelled ”No”, 5 labelled ”Yes”
Q11. Depending on your previous answers: Why? Why not?
Long text answer.
Answer listed below.
• If gaming regularly, the idea of the game could become ingrained subconsciously...
• transportation mode is bounded by several factors: available transports, distance, time. Someone with a car might need it because he lives far away from work, and the bus might have hard constraints (too early, too late, possibility of missing it, have to walk before/after, too many people, etc.). Even if a game makes you understand your impact, I think it have a low probability of changing your behavior.
• Game can engage people very well. If it is well designed, it can effectively change people's choice and habits.
• Experience of competitions to walk more have shown people are then motivated to move
• People are quite set in their usual lifestyle and do have reasons for the choice of transport: convenience, necessity, or others. Certain distances are better bridged by car. And some people hate unreliable public transport, waiting in the rain for a delayed bus or getting sneezed at in an overcrowded bus. A game will most likely not change this. A change in behavior may occur when circumstances are right, e.g. close distance which would allow walking, or convenient bus link e.g. a direct reliable connection without changing the bus. And a game may certainly trigger such a change, especially when there is some fun reward for walking or cycling. For me there is basically no other choice than car. I did walk a few times in summer - is 1 1/2 hours walk and is only OK in good weather.
• No Idea what this is about. will have to try first.
(Continues)
APPENDIX 9. (Continues) Pre-testing Questionnaire
(Answers to Q11 continues)
• It depends on the culture of the people, how people regard games, how intrusive it can be, how addictive it can be. If it's a "free" game there's probably lots of subliminal messages and adverts. If the player has to pay for it, why would he do so? How to get the players integrate that game into their daily lives, it has to meet the players' needs in some ways.
• I really don't know
• With The right approach (which i don't know-how what it is) possibly some impact couldnt be made :)
• I think it will
• It's possible that players change their behaviors while playing games but I doubt that it will stick.
• Learn people habits and show them alternatives
• If it is made correctly, and is aimed at the right points, it could seriously impact everyone who plays it.
• If Pokemon can cause traffic, anything is possible.
• It will motivate people, same idea like Fitbit has
Evergreen: A serious multiplayer Strategy/RPG game
Q12. How did you hear of this project? *
Check all checkboxes that apply.
• Recruited by the organizer as an initial volunteer.
• Recommended by a friend.
• Other:
APPENDIX 10. Evergreen: Evaluation Questionnaire highlights
Quantitative questions omitted. All questions text-based answers. None of the test-based questions were required.
Q1. Did you play any similar kind of game before? Mention examples.
• Mostly other old jRPGs, not anything similar on mobile that I can recall.
• no
• No.
Q2. What was bad with the game? What could have been better?
• It needs more "in-your-face-AAA-stuff-popups".
• Base-sharng, more players to test with, too few right now. More obvious showing of emissions and eased ways to
reduce it.
• A significant decrease in emissions if player was actually walking or biking on that day (ergo, transport detection
must be good).
Q3. If you were not influenced, why not? What would have had an influence on your choice?
• Because the effects of actual transport did not really feel like it was reflected in the game.
• the game can make me more aware of my action, but other factors are more important (distance, weather, time, etc.)
• I need my car to get anywhere since i live in <Omitted>. Otherwide I would have walked more or even tried the bus
• Not sure
Q4. If you have any other thoughts, please share them. Any feedback or ideas are appreciated.
• more feedback on the transportation choice at the end of the day? (you produced xx emission with transportation
today), a ranking/leaderboard, to increase competitiveness?
• I am the power.
• This game is a really good idea but there should be something to do while waiting for the next round to be played.
Some sort of mini games perhaps. It would be great if it was possible to play mini games where you gain or earn
something by walking or taking a bike ride. Perhaps you could scout for monsters that way? Or perhaps just gain
more knowledge about your surroundings and get even more berries and building materials?
APPENDIX 11. Tester Interview Transcripts Public game testing announced the 12th of April on Facebook.
April 23rd the Evaluation form was disseminated.
All chat with testers recorded below, starting on the 12th of April or later.
Each separate chat-exchange occasion is separated by a new line.
Exchanges have been formalized and de-contextualized to increase readability.
All transcripts were approved and verified by the interviewees after they had been
transcribed. Screenshots cited within the transcripts are available in Appendix 12.
Interviewee/Player 1: (code named Sparris)
-------------------------------
Author and Sparris exchanged screenshots of their game status (log messages of what
had happened the first day).
Sparris: Nothing happens if I click on event log. Can't I view it anymore?
Author: It requires having some log messages there. Try restart the app and hit 'new
day' again. It will make the text there clickable next time.
Sparris: It showed up when I restarted the app.
Sparris shows a screenshot of from the Transport Usage screen, where Idle is the most
detected mode, Boat being the second. (Sparris 1)
Sparris: Why does it say boat is the transport? But yeah, the graph has got Idle and
Foot quite right.
Author: Probably due to sampling of the boat transport.
Sparris: Why is there an update now?
Author: Only Facebook was updated. The game will update as usual in the evening (10
pm GMT).
Sparris: I just took this screenshot now. After I clicked update, it went to my
previous status. It should be day 4 already now.
Author: Either you are in single-player mode, or you are confused. I am also on day
4 now. There shouldn't be any problem.
Sparris: Alright.
Author: Do you want to fight? I can give you a Gladius (a weapon).
Sparris: Give it to me! I have nothing.
(Later on) Sparris: Why didn't you give it to me?
Author: I don't have you in the "Known Players" in-game. I am too busy dying at the
moment. Find me and I can give it to you.
Sparris: So, the action to look for you will manifest later?
Author: That is correct. All daily actions manifest as the turn updates (at 10 pm
daily).
Sparris: Alright!
Sparris: I just posted on Assault of the Evergreen's Facebook page. Is that OK?
Author: Yes.
Sparris: You still didn't give me the Gladius (the weapon)! I already found you and
sent a message "hi" to you.
Author: That is what I was thinking about. Just because you sent me a message does
not mean that I can reply or send you things. So maybe I should add in the server
that if you send a message, the other player will automatically get to know you?
Otherwise I was considering adding an action to "Inform player whereabouts". So that
you can spread connections more easily. Do you think it is needed?
Sparris: Indeed. I think it would be better if you get to know the sender and can opt
to connect or not.
Author: That is not up to the receiver. It should be up to the sender. Maybe a "Share
known players" action would be needed, where the recipient will get to know all that
you know.
Sparris: Yes, maybe like that.
Author: The server has been updated. Try to share knowledge to me. And please check
the transport usage for the past 2 weeks. Print screen, and tell me what is correct
and incorrect with the percentages.
Sparris shared a screenshot (Sparris 2)
Sparris: No car it seems, although I drove last monday. I shared knowledge with you
in-game now.
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Author: Are you sure that you shared? Hm. Maybe I'm not saving every action. When I
query I am not seeing the message, so maybe the data of all players is only saved
after each new turn right now, and not after each (your) request. So when I killed
the server to restart it some data was lost. So maybe the game should save the file
after each request.
Sparris: Yep.
Author: For now, can you just resend the knowledge sharing?
Sparris: Now there are no known players for me! Maybe I have to search for you again.
Author: That could also be my fault. I will diagnose the save file. Wait. Try now and
update. I hopefully fixed the code now.
Sparris: I shared the known player whereabouts now.
Author: I send you the Gladius (weapon) now. Try equipping it. Did you receive it?
Sparris: I have received and equipped it! :D
Author: Can you give me some resources? I need materials.
Sparris: How much do you need? Is 6 enough?
Author: Yeah, that would be good.
Sparris: Mutated shrubs almost killed me!
Author: Oh, my.
Author: By the way, did I send you some item earlier already? Should I send you
something more? I have some new gear, Harvesting tools among them.
Sparris: Yeah, I got a Gladius from you.
Author: I send you some new items. Equip the tools and you should get even more food
when you look for food later.
Sparris: Alright.
Author: We are thinking of the future of Evergreen and would like some feedback.
Author shows Sparris a plan of new features to add. Features include new icons,
localization to other languages, adding a tutorial, improving or removing transport
mode detection, server lifetime, maximum players per server, removing dead/inactive
players, adding a disclaimer for the transport mode detection that it may not be
accurate, and price to pay for the app.
Sparris: Alright. I will read it. Pay or no pay for the app?
Author: When browsing the Android Play Store, yes. Most games cost, and there is a
perceived value in increased costs.
Sparris: I think you should start with a free version, and include an in-game store.
Author: What kind of add-ons?
Sparris: For example access to more tools and weapons.
Author: Monetization via in-game purchases is very common, we but haven't considered
it earlier. There are also balance issues since it is a multiplayer game.
Sparris: Alright.
Author: Does the rest look good, or what?
Sparris: Revival possibility is good.
Author: I added in-game purchases as a possible feature.
Sparris: I am thinking that you could do like the Supercell start-up. If I remember
correctly, Clash of Titans was free. I was trying to look for the info, but the
browser is so slow. First you need to attract people to play the game.
Author: That is another question entirely. We are not really caring about the amount
of players at the moment, but rather of the quality of the playing experience.
Sparris: You would have to put a price that a person would not fell like they are
spending. 0.99 euros for example.
Author: Are you still playing the game, by the way (April 23rd, 11 days into testing)?
Sparris: Aha, once a day.
Author: Is there anything you feel that is missing?
Sparris: Putting a disclaimer that transport detection is of low quality is maybe not
a good idea... better yet remove it if it cannot be improved... or does keeping it
eventually help in improving the detection?
Author: Not by just keeping it, no. We would require more user interaction or gathering
more data to improve it.
Sparris: You could maybe give the gamer an option to help gather data in return for
a free berry :D
Author: A free berry for each 5 minutes of data?
Sparris: 15 minutes. More berries for data that is difficult to gather.
Author: That would mean integrating the transport data gathering app into the game
app.
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Sparris: Yes.
Author: And have a button to upload it to the server. Then I could analyze the data
and give berries if the data is good?
Sparris: Yes, since you really do need to improve the detection. You should give
berries automatically. You could add ranged weapons? Like bows?
Author: If you stop focusing on the plan and think about the gameplay so far. Do you
like it? What do you like? What don't you like? Anything that you feel missing?
Sparris: Mmm.. I like it. I am just missing ranged weapons.
Author: How do you think ranged weapons should/would work? A few free attacks before
melee combat?
Sparris: A few free shots depending on the level of ranged weapon, yes, before melee.
I don't know how to improve interaction with other players... can you accidentally
bump into someone without searching for them explicitly?
Author: Yes, you can when you are scouting. We could possibly add so accidental player
discovery to other actions as well, perhaps.
Sparris: Because I think for some, scouting is not a priority.. so chances of bumping
into another player will be rare... maybe boring.
Author: Indeed. Bon (another player) was playing mostly solo, for example, even though
he is also on the multiplayer server.
Sparris: Are we on day 10 in-game? And there has been no encounters with other players
yet, at least not for me.
Author: There are too few people actually playing it, decreasing chances. With more
people it would be more chaos and player discoveries would occur much more frequently.
Sparris: And if we encountered another player, one could challenge the other to fight
or just trade goods or just move along.
Author: All of that is already possible, yes, just like we traded resources and items.
We also tested stealing and fighting in the test-phase before the public tests.
Sparris: Yes, but we did not 'meet'... I had to use the "Search for player" action.
Author: Of course, but we met after searching.
Sparris: Like, maybe instead of just meeting random monsters, one can also meet random
players.
Author: That has been added to the "Scout" daily action, as I mentioned. Or you meant
that you want AIs as well? Interactable ones, that may request and give you something.
Sparris: Yes, but I mean you do not need to Scout to meet monsters.
Author: That is the whole point of the game: that the Evergreen wants to wipe out
humanity due to all emissions. So, yes.
Sparris: Hmm.
Author: Just like in some other role-playing games (e.g. Final Fantasy series) you
can run around in circles and just constantly fight monsters - if that is what you
wish to do. If you want to meet other players or progress the story usually you have
to go to cities and look for interactable players or NPCs (non-player characters,
AIs).
Sparris: Then maybe it is fine.
Author: You will not meet people unless you are actually looking for them (say, for
example, in a city). Now consider yourself in a post-apocalyptic scenario and the
city has been destroyed by monters. People will be spread out. People would not
necessarily be so easily found. Thus, the "Look for Players" action - which enables
you to look for any player.
Sparris: Aha.
Sparris: Hey, was it so that HP recovers automatically every day without doing the
"Recover" (daily) action?
Author: It should, yes, but very slowly. Maybe it should be updated to be like 2 HP
per day or something. Right now it might only be 1 HP per day.
Sparris: Yes, make it 2.
Author adjusted the History set size used in the transportation mode recognition after
roughly 1.5 weeks.
Author: Did you download the new version which I gave you? Have you checked the
transport usage the past few days with it? Has it felt more correct?
Sparris: I did download the new one and just checked usage now. It shows Idle as
highest, but is not showing car or foot so much, even though I have been walking and
taking the car a bit. Then there is Boat which is always present for some reason...
(see Sparris 3)
Author showed Sparris an updated detailed long-term plan. (Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Sparris: Crafter's garb... to withstand the heat of the flame.
Author: See in-app purchases as well, just some ideas. "Explore" active action would
make people walk more. Opening the app before and after the walk, gaining bonuses
based on duration they walk.
Sparris: I only see "Exploration Insignia" and "Veteran's memories" in this file I
have.
Author: Yes, we do not want to add any items yet.
Sparris: Aha.
One month later (24th May) Author asks again.
Author: If you look at the transportation usage in Evergreen post update (dun remember
when) did the transportation detection feel more accurate?
Sparris shows some screenshots. Idle is being detected. Boat is as usual always
present as a false positive. Foot is being detected as well. Bus is being detected as
a false positive.
Sparris: It doesn't seem so accurate.
Sparris sends a screenshot of the Transport Usage screen after walking home (Sparris
4). Foot is detected properly. Boat is the largest false positive as usual.
Sparris sends a screenshot for when walking from a public event area (Sparris 5). In
it Foot is being detected accurately, with Bike being a significant false positive.
Interviewee/Player 2: (code named Stone, transcribed from Swedish)
-------------------------------
Author: The game has been published now. You should create a character in the game.
But the next day update is in around.. 20 hours, so you can easily do it tomorrow as
well. Then we must crush everybody who will join the game (jokingly)! If we are to
have some co-operation, maybe one can gather resources while the other is crafting?
I have been focusing on "Inventing" in the beginning, anyway.
Stone: I will do it tomorrow. I can get the resources. :)
Author: I suggest levling up Foraging for gathering food and Scanvenging for gathering
Materials. Without them it will be rather slow.
Stone: Yes, I have tested both with and without them (in Singleplayer mode). It makes
a huge difference when they increase in levels! :D
Author shows Stone a screenshot of his progress.
Author: I failed to invent anything the first day at least...
Stone: I hade so much to do yesterday that I forgot to play the game.
Author: You can start now.
Stone: I have begun to gather berries and teaching myself to get better at Foraging.
Author: I got 0 materials after the last turn. I need to gather some first.
Stone: I am not sure if the game is working for me. Should we not have played the
days turn now?
Author: In one hour, the update will be at 10pm GMT.
Author: Oh, yeah! I made a Knife! Do you need it? Should I search for you? What is
your in-game name, if so?
- No response from Stone (same day)
Author: I almost died!
- No response from Stone (2 days without response)
Author: Hey. (4 days after last response)
Stone swears a lot and explains that he has not received any notifications from my
messages on his devices for days. He also says his in-game name.
Stone: I have a lot of food and materials that I could share with you.
Author: Cool, you would just need to find me to give it then! I went and died, but I
have some gear so that I can craft more items.
Stone: I have not met any monsters yet. What is your name?
Author gives his in-game name.
Stone: There we go. :)
Author: I got a Fighter's Armor +1 randomly while walking. It is crazy.
Stone: Nice! :D
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Author: I updated the game, by the way. See the e-mail or on Facebook.
Stone: I saw the mail. I will update when we get home.
Author: Damn you sent me a lot of resources! Nice! Is there any special gear that you
want? I can craft. By the way, you must send me a "Share Known Player Whereabouts"
active action to me in order for me to send stuff to you. Otherwise I would have to
look for you myself - and that would take some time.
Stone drifted off into other conversation topics without replying what he wanted.
End of testing phase, 23rd of April Interview/Discussion.
Author: I am thinking about some things: does the game need more content (maybe
single-player story, AIs, pictures) or? Aim to get Evergreen a public release on the
Android store.
Stone: One thing I have been thinking about is when you have built a weapon or
something, should one not get a larger picture saying "TA-DAAAAAAAAAAA!!! Look what
you just made!"
Author: I am wondering about the timeline for publishing, anyway.
Stone: How complete are the multiplayer parts? Should the single player game have
some story that you follow or should it be the same as multi-player minus other
players?
Author shares a draft of plans with Stone.
Author: The multiplayer part is basically done. If one wants to add more features,
then that is feasible, but it will always change the balance of the game, which
requires testing for each feature you would want to add. Some brainstorming may be
needed.
Stone: I am thinking about weapons. Can one make more than one type of axe, for
example?
Author: I may not have been very clear. I will clarify. When inenting weapons right
now there are 10 different types. The same applies for crafting. Then there are
quality levels that affect how and which statistics they get.
Stone: Will the better quality weapons have different appearances?
Author: Pretty much.
Stone: One could make some variations of each weapon and give them a finish each. The
first ones rusty, maybe the sledgehammer could be made of stone, etc.
Author explains how that is pretty much the current idea.
Stone: Maybe it would be good to accompany any visual representations of the weapons
with a number to display in some sense how good or useful it is. And it would also be
really nice if you got a big pop-up with a picture of the weapon when you have just
succeeded crafting it.
Author agrees to the general idea.
Author: If it is to be published, other questions arise, such as payment ,duration of
server, maximum numbero f players, number of servers, etc. The transport detection
right now is not optimal either, so the question is if it should be torn out and
randomized, kept in a sub-standard state, or spend time and resources to improve it.
- Stone didn't reply until later and missed the question.
Author gave a link to the evaluative questionnaire.
Author: Can you please fill in the evaluative questionnaire.
Stone: Oh, I missed that you had written to me again. :(
Author: I see you put a 1 on Character customization (in the evaluative questionnaire).
Why is that?
Stone: It crashed the first time I tried to pick character (avatar). So I played with
the default character that I was given. That's why I gave it a one. :P
Author: Even in the multiplayer mode? Usually it would only crash in the single-
player mode.
Stone: Yep. I must have cryptonite in my cellphone. Instead of regular minerals.
Author: It seems you missed a question. You may go back to the questionnaire and edit
your previous response.
Stone: Nice! When one knows that it is a work-in-progress then the evaluation becomes
different. Like, things will get fixed. There will be more characters later, and maybe
a tutorial and more help-sections will be added. If one needs a lot of help to get
started, that is. Maybe a small tutorial.
Author: Indeed.
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Stone: That one then can choose to skip. There. I filled in the questions I had
skipped last time. The only thing I can think is sad/boring/not good is that I cannot
play so much each day. I would like that there was more things to do in the game than
just wait for the next turn. Some kind of mini-game perhaps.
Author: Indeed, promenade/walk-based mini-games with specific goals would be cool
indeed.
Stone: It would help me exercise more. Kind of like how Pokemon Go (a sarcastic
negative phrasing of the game name was used) made people walk around and look for
monsters.
Author: Yes, precisely.
Stone: The difference is that I like this game. :P
Author quotes an old question to Stone concerning the transport usage and its perceived
correctness.
Stone: I am running the newest version of the game app. I took a screenshot I intended
to send.
Stone sends a screenshot (Stone 1). Idle looks decent, Car is being displayed as
disproportionally highly used (139k seconds the past 2 weeks, or 38 hours), and most
others have low (noise) values.
Author: I suspect that you have not been driving more than you have been sleeping.
This means the detection is broken. Can you take a screenshot with just 1 day, or 3
days?
Stone: I will, later. :)
Author tries to contact Stone to no response for 3 days again. More problems with the
communication software and devices.
Interviewee/Player 3: (code named Bon)
-------------------------------
Bon: Good morning. Choosing an avatar in solo-mode of the game crashes it. It then
returns to the menu.
Author: Indeed. It happens only on some devices it seems.
Bon: I guess I will use the basic face (avatar) then. By the way, why is the game
conducted in 24 hour turns and not 12 hours, or any other amount of time?
Author: Well, we could consider using 12 hour turns, but we will start off with 24
for now, since 12 provokes the question when to update during the day. Even casual
players checking in once a day should not be penalized, is my reasoning.
Bon: Indeed. It was just a question, because I played some small games in the past,
and it allowed one action when I woke up, and one before going to bed. But yeah, the
system should not penalize players who cannot spare so much time as well.
Author: My thought precisely.
Bon: Also, does it have push-notifications when a new day starts, to help users
remember? I know it cna help the first time, but then it can become extremely annoying
later on.
Author: It kinda does, it just works miserably - only inside the app itself. I didn't
have time to fix it. I thought that I would do a Facebook post to remind players in
the meantime. Every night or morning.
Bon: I guess that kind of stuff can impact how long the user will keep playing the
game.
Author: Yes, many factors impact the user experience.
Bon: That is true.
Author: I will probably gather feedback and iterate the game after 1-2 weeks. Did you
try single player first, or went straight into multiplayer?
Bon: Singleplayer first. I played a few days. I put way too many tasks on the first
day, then got the advice (that you should pick less than 4 or 5 to remain efficient).
(Sarcastically) Damn character cannot do 20 things at the same time. (Sarcastically)
What a loser.
The Author laughs.
Bon: Then I almost died, was walking naked outside it seems like.
Author: Or almost, yes. Some gear and combat skills are good if you don't want to get
knocked out early on by the attacking monsters.
Bon: Crafting a weapon does not automatically equip it?
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Author: Nah. We should perhaps change it for the initial weapon - so that it gets
equipped automatically, but for subsequent weapons it is not as obvious (if they
should get automatically equipped and change the currently equipped weapon).
Bon: I had to delete my character to start the multi-player game. I couldn't switch
back to the main menu - it was the easiest way to do it.
Author: Indeed. It is possible to hit the back button sometimes, but that issue has
not been fixed yet. We are aware of it.
Bon: I guess it's "Change Character" (an in-game screen)? Because "Quit Game" does
what it says.
Author: That ("Change Character") allows creating new characters within the same game
mode (single/multi-player). I didn't add a toggle for single/multi-player in that
specific screen though. Change Character works if you managed to create both
characters before, anyway.
Bon: Oh, alright.
Bon shows a screenshot of when walking to the coffee room at his office (Bon 1). The
app had detected Foot properly, but was displaying Bus as detected falsely.
Bon: I did not take the bus. I went to the coffee room, the cafeteria and played with
my rolling chair.
Author: I will actually request similar screenshots later, so you can save more if
you find it is working decent or bad. Longer periods of time preferred. For bonuses,
any transports over 300 seconds the past day are considered.
Bon: I hope Idle offers a lot of bonuses :D
Bon sends another screenshot (Bon 2), this time displaying 1 week. It shows only a
total of 940 seconds for Idle, some Foot, falsely detected bus and low, probably
noise-induced, time durations for the other transports.
Bon: But yeah, I will keep you updated on it. I don't know how you check exactly the
transportation type, but is duration take into account? Bus usually takes more than
1 minute.
Author: Not really, right now. Idle is neutral (no specific bonuses or penalties).
Bon: Evergreen monsters shouldn't find me if I stay geeking inside all day long! It's
a scam! XD
Author: They can smell you! ;P
Bon: Damn, they're smart.
Bon shows another screenshot 1 day later (Bon 3), again showing a very low total
amount of seconds (almost 2k for 2 weeks of time), and Boat being detected 2nd most
often after Idle (which seems to be common for all nearly all qualitative tests by
now).
Bon: Do I walk as fast as a boat? :D
Author: (sarcastically) It seems so. More likely it is confused with Idle or other
transports. Walking is usually easy to identify.
Bon: I did have to walk very fast yesterday, so could be that also. But yeah, car/tram
are being detected when I in fact have been Idle.
Author: Did you have the mobile in your pocket while working, or actively been using
it?
Bon: When walking yesterday it was mainly in my pocket. When tram and car were being
detected it was mostly in my hands.
5 days later Bon sends a another screenshot. Again it is supposed to represent 2 weeks
of data, but contains only around 7k seconds worth of detected transports.
Bon: I only walk, no other transportation. Bus and boat are usually (being detected)
when I'm idle/doing small movement with my phone in hand. I think I saw Bike being
detected when I was walking last time.
Author: I saved your comments, and am almost done with feedbacks.
Bon: But what if I have more feedback on the game too? :D
Author: Then you can provide that as well. I forgot to mention that. :P
Bon: I will feedback that feedback. You will see.
Bon sent an e-mail reply with feedback as response to an e-mail I had sent addressed
to all possible testers asking for feedback. The contents below:
- For emission production, I never saw anything related to transportation in
the logs. Maybe my motorized transports are not important enough, but is there feedback
regarding emission when you use them?
- what are the gain of scouting the area? I found no interest in it at the
beginning, and just gather food or resources when I need them.
(Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
- should the item description explicitly name the resource associated? Right
now scavenging, foraging + value (related to skill name)
- How skill improvement works? Do we absolutely need to study, is it parallel
to action, i.e. the skills selected for the day will improve? Study gives xp, but for
what? (less important, the yellow progression represents the total progression or
towards the next level?)
- still don't know if it's possible to go back to the main menu to change from
singleplayer to multiplayer, and creating a new character seems to do it on the same
type (solo/multi).
- Is co-op that important? Haven't seen anyone, didn't try to find anyone, no
emphasize on it
- defensive training affects the spawn of monster? or similar to parrying?
- small tutorial for the first day? might be hard to implement/not extremely
useful
I think that's all right now
As a reply to clarify, Author replied the following:
- Transports affect most actions in the background through an aggregate
multiplier, random events may also be generated if u use a particular transport
enough.
- Scouting - u can find items, other players and encounters as well
- Skills are trained whenever u gain EXP, which is initially 20 or so,
daily 1 or 2 points, from encounters (varies) and from the Study action. Updates to
the buttons mean a new level has been reached.
- Indeed, still didn't fix the single/multi,
- Co-op should help since it eases specialization (e.g. one gathers stuff,
other crafts, or some other combo). At least where training skills is concerned.
- Defensive training basically increases the Defense by 1 point per level
(makes them miss more).
Seems to be mostly how the game works - which I intentionally left to be figured
out by players, but I guess adding more FB posts to clarify or expanding help-pages
in game or on a web-page could help that?
5 days later, Bon reported again a screenshot with overall low total seconds (around
6k for 3 days), with all kinds of transports being falsely detected.
Bon: Bike, tram, train, car, plane and boat still incorrect. I did use the bus last
week, but I think it was more than 3 days ago.
Bon goes on to ask how the implementation is done and suggests improvements. I explain
how it is implemented and that noise removal is already there to some extent (via the
History set).
Bon: But do you have the same behavior on your phone, or are my sensors really noisy?
Author: Right now mine is super accurate, but I've only been Idle at home, so it's
not a good comparison. What I notice in your graph is that Idle is relatively low. In
most others Idle is usually the highest of all by far. So some sensing might be
working differently, or sleeping alltogether on your phone. On other devices 50 to
90% of all detected seconds should be Idle - as we live mostly sedentary lifestyles
(at least the testers), then various degrees of the remaining time should have been
distributed somewhat similarly to what modes of transportation you have been using.
Bon: Well, with the two weeks view Idle is first, but it is not far from the others.
But all the wrong stuff (bus, car and all) should be idle in reality.
Bon shows another screenshot, with the Graph display duration set to 2 weeks. Idle is
at only 1080 seconds, Foot at 910, Bus at 790, etc.
Author: Yes, 1k Idle seconds is very low.
Author sends a screenshot of his results, showing more than 28k Idle seconds being
detected for a period of 3 days, with low seconds amounts for all other transports
(Author 1).
Author: 3 days, 28k seconds.
Bon: Indeed. (Continues)
APPENDIX 11. (Continues) Tester Interview Transcripts
Author: Maybe your phone likes to kill the transport classifier service or something,
while you are not using it actively. >> This means that we would need much more time
and devices to test on to perfect the code to make it work similarly on all devices.
Bon shows a screenshot of teh app from a status screen, displaying how long the
application has been running, including its background services. It has only been
running for 11 minutes. See picture Bon 4.
Bon: 11 minutes, so, yeah, my phone doesn't liek you, it seems xD
Author: Hm, that is the timestamp of when it started? Usually it should restart when
you leave the app, or starting the app again, loading saved data each time, so it
should be fine. It might be something in the sensing thread or classifier then.
Bon: It was a time counter since launch of service, yeah. I will try tonight and check
the same values before launching the game. See if it's still running then.
Bon: My phone did kill your app.
Author: Interesting.
Bon: Stupid phone, I guess.
Author: Or it doesn't like background services using a megabyte of memory or writing
to disc every now and then.
May 11th, almost 1 month after the game was launched publicly. Author discovers Bon
is still playing the game, based on server records.
Author: You are still playing Evergreen, eh? Seems like transport detection is never
working for you.
Bon: Still playing, yup.
Bon sends another screenshot (Bon 5).
Author: Cool. Well, Idle looks more correct at least (but still low for being 2
weeks).
Bon: Foot is way too low, but I did use the bus this week.
Author: Looking at the "daily" data sent to the server, then bus or some transport is
always on top for you, but never more than like 500 seconds.
Bon: Should have 20 mins of bus yesterday, and 40min of walking daily more or less.
I guess my sensors are always sleeping when my screen is off. You should probably
ditch out my data (Bon contributed some data to both the initial transportation sample
gathering for training the classifiers, in addition to the game/qualitative testing).
Author: Mm, must be, or the app thread is sleeping. But I will report your results
anyway, that even if it works on one device it did not work on some other.
4 days later, Bon sends a screenshot of the battle log from the game.
Bon: Freaking rock monster! More than 100 lines of text to see the beginning of the
fight.
Author: Did you win?
Bon: It was a looooong fight. And noooo. :(
Author writes a consoling gesture: *patpat
50 days have passed.
---------------------
Bon is still playing the game at the time of this writing (05-29, 50 days after game
launch). Sparris is still playing, but took some weeks’ break (2-4 weeks). Author and
Stone stopped playing shortly after the 10-day test period was reached.
Bon: I am still playing, I want to see the max defense level.
APPENDIX 12. Tester Interview Discussed Screenshots
Sparris 1 Sparris 2 Sparris 3 Sparris 4
Sparris 5 Stone 1 Bon 1 Bon 2
Bon 3 Bon 4 Bon 5 Author 1
top related